@leadbay/mcp

GitHub Actions

Model Context Protocol (MCP) server for Leadbay — AI lead discovery, qualification, and enrichment for Claude Desktop, Cursor, and Claude Code.

Devops Developer Tools

Add to Cursor Add to VS Code Run on PlugMCP

GitHub npm Website

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "leadbay-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@leadbay/[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y @leadbay/[email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add leadbay-mcp -- npx -y @leadbay/mcp@0.46.1

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "leadbay-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@leadbay/[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.46.1
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install @leadbay/mcp?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does @leadbay/mcp need an API key?

No required environment variable is listed on this record.

What transport does @leadbay/mcp use?

@leadbay/mcp runs locally over stdio.

When was @leadbay/mcp last checked?

Last checked 2026-10-28. Model Context Protocol (MCP) server for Leadbay — AI lead discovery, qualification, and enrichment for Claude Desktop, Cursor, and Claude Code.

From the publisher

Documentation

How Leadbay thinks (mental model for your agent)

Inbox, not a database. Each day your user logs back in, a fresh batch of leads is delivered. Batch size is paced by how many leads the user has actually acted on recently — some workflows produce a big stream of smaller prospects, others a narrow stream of bigger ones. Pulling more won't produce more; acting on leads does.
Two scoring layers. Every lead ships with a basic score (firmographic — already decent, usually correlates with AI). Roughly the top 10 of each batch are also AI-qualified (targeted web research + qualification questions → ai_agent_lead_score). Leads below the top 10 aren't worse — the system is saving resources. The agent can request deeper qualification (leadbay_bulk_qualify_leads) or contact enrichment (leadbay_enrich_titles) on any lead that looks worth it.
Daily rhythm. The agent works best as a daily check-in: pull fresh leads, skim the auto-qualified top, deepen 1-3 promising ones, propose outreach, then log what actually got sent via leadbay_report_outreach. If your host supports scheduling, set up a daily run.

For users

Get Leadbay MCP running inside your AI assistant in a couple of minutes. No coding required.

New to Leadbay? The friendly, screenshot-driven walkthrough — what a lens is, how scoring works, and the full MCP setup for every assistant — lives in the Leadbay user guide. This README is the technical companion.

No Leadbay account yet? Create one here first — you'll need it to sign in during setup.

Connect on the web (no install)

If you use Claude on the web, Claude Desktop, or ChatGPT, the fastest path is a custom connector — no terminal, no tokens to copy. Add one URL and sign in with your browser:

Name: Leadbay
URL: https://mcp.leadbay.app/mcp — one URL for every region (/fr/mcp remains a compatibility alias)
On ChatGPT, use https://mcp.leadbay.app/chatgpt/mcp instead. Same server, same sign-in, same leads — but the assistant cannot generate a top-up link or open your billing page there, because the OpenAI app directory does not allow an app to sell credits. Buy credits or change your plan in your Leadbay account instead.
On any other assistant (GitHub Copilot / VS Code, Goose, Cursor, …), use https://mcp.leadbay.app/apps/mcp. Same server, same sign-in, every region.
On ChatGPT and those assistants, today's leads open as the Lead Triage Board right in the chat, when the assistant can display it. Claude keeps its own widgets and artifacts on /mcp.

In Claude: Settings → Connectors → + → Add custom connector, paste the URL, then open the connector and Connect. Sign in with Leadbay, click Approve, and you're linked. The server handles OAuth in-app; updates are automatic — you never touch a config file.

Install in Claude Desktop (one-click bundle)

Prefer a bundled desktop extension? Grab the one-click file.

1. Download the extension

👉 Download the latest Leadbay MCP for Claude (.dxt)

On the releases page, click the file ending in .dxt to download it.

2. Install it

Double-click the downloaded .dxt file. Claude opens and shows an install dialog — click Install, and you're done.

If the double-click doesn't open Claude, install it manually:

Open Claude and go to your profile → Settings → Extensions.
Open Advanced settings.
Choose Install extension… and select the .dxt file you downloaded.

3. Sign in

Claude will prompt you to connect Leadbay. Sign in with your Leadbay account and you're ready — just ask your agent for leads.

Using a local assistant?

Leadbay MCP also works with Claude Code, Claude Desktop, Cursor, and Codex. The universal installer sets everything up for you and lets you sign in with Leadbay.

Requires Node.js 22+. Then run:

npx -y -p @leadbay/mcp@latest installer

It opens in your browser where you click Sign in with Leadbay, then pick which assistants to connect. Works on macOS, Windows, and Linux.

To uninstall, run the same installer with --uninstall:

npx -y -p @leadbay/mcp@latest installer --uninstall

It opens an uninstall window showing only the assistants that have Leadbay connected — pick the ones to remove and click Remove selected. It only removes Leadbay; your other settings and connections are left untouched.

Ask for your first leads

Open a new conversation and describe the outcome — you never name a tool, just say what you want, the way you'd ask a colleague:

Show me today's leads and tell me which two are worth opening first.

A successful first reply is a ranked table of prospects, not a wall of text: each row has a fit score, a one-line why-it-fits, and the best contact to reach. Then keep going:

Research the top one — is it a fit for us?

Draft me an outreach email to them.

I just emailed them. Log it as outreach.

For developers

Everything below is for contributors and anyone running Leadbay MCP from source or wiring it into automation.

Install a local version with the custom installer

To run your local checkout (instead of the published package), first build it from source:

pnpm install
pnpm prompts:build
pnpm -r build

Then point the installer at your freshly built version with --local:

pnpm --filter @leadbay/mcp installer -- --local

--local registers the MCP client(s) against the build in your working tree rather than @leadbay/mcp@latest. OAuth is handled automatically — you don't need to pass --oauth. The installer asks per-target before writing anything.

All install methods

Every supported way to connect Leadbay MCP:

Method	Command / action	Platforms	Notes
Hosted connector (no install)	Add custom connector → `https://mcp.leadbay.app/mcp` (all regions)	Claude web / Desktop	Browser OAuth in-app. Nothing to install; auto-updates.
Hosted connector — ChatGPT	Add custom connector → `https://mcp.leadbay.app/chatgpt/mcp`	ChatGPT	Same server; the top-up and billing tools are not registered (OpenAI directory rule).
`.dxt` / `.mcpb` bundle	Download from Releases, double-click → Install	Claude Desktop	One-click desktop extension.
Guided installer (GUI)	`npx -y -p @leadbay/mcp@latest installer`	macOS, Windows, Linux	Browser wizard: sign in with Leadbay, pick clients. Works for everyone.
Local dev build	`pnpm --filter @leadbay/mcp installer -- --local`	macOS, Windows, Linux	Registers clients against your local build. OAuth automatic. Build from source first (above).
Claude Code plugin marketplace	`/plugin marketplace add leadbay/mcp` then `/plugin install leadbay@leadbay-mcp`	Claude Code	Registers the MCP server and installs auto-triggering skills.

What each installer writes per client

The GUI/CLI installers only touch clients that are actually installed on the machine:

Client	Installer behavior
Claude Code	Registers/removes `leadbay` with `claude mcp add/remove --scope user`
Claude Desktop	Writes/removes only the `mcpServers.leadbay` entry in `claude_desktop_config.json`
Cursor	Writes/removes only the `mcpServers.leadbay` entry in Cursor's MCP config
Codex	Writes/removes only the `[mcp_servers.leadbay]` block in `~/.codex/config.toml` and the Leadbay-managed shell export block

Claude Code plugin marketplace

/plugin marketplace add leadbay/mcp

/plugin install leadbay@leadbay-mcp

Claude Code prompts for Leadbay auth/config. Registers the MCP server and installs a set of skills that auto-trigger on natural-language asks — including leadbay_daily_check_in ("get my leads today"), leadbay_research_a_domain ("research acme.com"), leadbay_followup_check_in, leadbay_qualify_top_n, leadbay_refine_audience, leadbay_log_outreach, leadbay_import_file, leadbay_plan_tour_in_city, leadbay_prospecting_overview, leadbay_extend_my_lens, leadbay_setup_team_prospecting, leadbay_build_campaign, and leadbay_work_campaign. Each SKILL.md is generated by @leadbay/promptforge from the same source as the MCP prompts, so the two surfaces never drift.

Uninstall

npx -y -p @leadbay/mcp@latest installer --uninstall

Opens the uninstall wizard — only shows clients that already have Leadbay MCP configured. De-registers Claude Code, strips the JSON stanza from Claude Desktop / Cursor configs, removes the [mcp_servers.leadbay] TOML block from Codex, and strips the managed export LEADBAY_* block from ~/.zshrc / ~/.bashrc. Uninstall is scoped to Leadbay — it never rewrites unrelated client settings or removes other MCP servers.

Tools

Your assistant calls these on your behalf — you never call them directly. You ask in plain language ("show me today's leads", "research acme.com", "log that I emailed Jane") and the agent picks the right tool. The default surface below is always exposed; the full per-tool reference lives in the user guide.

Reading tools (always on)

These answer questions about your account. None of them creates, deletes or sends anything. Some of them do write one small thing back while answering — which leads you were shown, or the filter you asked for — and the table says which, because that is why they are not labelled read-only over the wire.

Discover & follow up

Tool	Description
`leadbay_pull_leads`	Pull today's fresh batch of scored, ranked leads. Records each one as seen, so it rotates out of tomorrow's batch
`leadbay_pull_followups`	Pull the leads that need a follow-up action. Saves the filter when you ask for one
`leadbay_account_status`	Check quota, credits, and account state
`leadbay_scan_portfolio_signals`	Scan your existing leads for a web signal in one pass ("which of my leads acquired a company since 2025?") — no quota burn. Saves the filter when you ask for one

Research a company

Tool	Description
`leadbay_research_lead_by_id`	Deep-dive research card for a known lead — details + AI qualification + contacts in one response. Records the lead as seen
`leadbay_research_lead_by_name_fuzzy`	Look up a lead by company name or domain when you don't have its ID. Records the lead it finds as seen
`leadbay_account_history`	Full history on one account — current AI signals + all notes + interaction timeline, in one call ("why has this account resurfaced?"). Records the lead as seen
`leadbay_prepare_outreach`	Build a personalized outreach brief for a lead. With enrichment on, it also orders the contact's details

Travel & field sales

Tool	Description
`leadbay_followups_map`	Geo-cluster your follow-ups on a map for travel planning. Saves the filter when you ask for one
`leadbay_tour_plan`	Build a visit itinerary for an upcoming trip to a city. Records the new leads it shows as seen

Campaigns

Tool	Description
`leadbay_list_campaigns`	List your existing campaigns
`leadbay_campaign_progression`	Show a campaign's funnel metrics
`leadbay_campaign_call_sheet`	Pull the call sheet for a campaign

Lenses, audience & qualification

Tool	Description
`leadbay_list_sectors`	List the real sector taxonomy labels — so you (and the agent) name sectors correctly, no guessing
`leadbay_list_previously_enriched_titles`	Recall the job titles previously enriched by the org (use before `leadbay_enrich_titles`)
`leadbay_list_lens_seed_candidates`	Read-only discovery surface for building a bigger lens
`leadbay_get_qualification_questions`	Retrieve the org's AI-agent qualification questions (how leads are scored)
`leadbay_get_lead_custom_fields`	Retrieve the custom-field values stored on one lead. Records the lead as seen
`leadbay_list_mappable_fields`	List the CRM fields you can map an import onto. Given sample rows, it uploads them to get the backend's mapping hints

Imports & jobs

Tool	Description
`leadbay_import_status`	Status of a running import job
`leadbay_qualify_status`	Status of a running qualification job
`leadbay_bulk_enrich_status`	Status of a running enrichment job
`leadbay_resolve_import_rows`	Map imported rows back to their lead IDs

Team, billing & product signals

Tool	Description
`leadbay_team_activity`	Manager-facing per-rep leaderboard + activity trend (non-admins are scoped to themselves)
`leadbay_create_topup_link`	Generate a Stripe top-up link (you pay in your browser — nothing is charged automatically)
`leadbay_open_billing_portal`	Open the billing portal
`leadbay_acknowledge_notification`	Clear a terminal bulk-job notification so it stops resurfacing
`leadbay_report_friction`	Report a problem to the Leadbay team — asks you first, and shows you what was sent (no account change)
`leadbay_get_artifact_runtime`	Fetch the headless view-models the agent uses to build an interactive HTML artifact

Write actions (on by default since 0.3.0; set `LEADBAY_MCP_WRITE=0` to disable)

These take action on your account. Every action is one you could take yourself in the app — there's nothing destructive at the platform level, and deletes are confirm-gated.

Qualify & enrich

Tool	Description
`leadbay_bulk_qualify_leads`	Trigger AI qualification on a batch of leads
`leadbay_enrich_titles`	Enrich contacts by job title
`leadbay_enrich_contacts`	Enrich one specific person (email / phone) — the contact you name, not a job title

Outreach & activity

Tool	Description
`leadbay_report_outreach`	Log an outreach action (call, email, meeting) — required after every contact
`leadbay_add_note`	Add a note to a lead
`leadbay_like_lead`	Mark a lead as liked — teaches your taste profile
`leadbay_dislike_lead`	Mark a lead as disliked — teaches your taste profile

Contacts

Tool	Description
`leadbay_add_contact`	Add a person to a company (name + optional LinkedIn / title / email / phone)
`leadbay_remove_contact`	Remove a contact you added
`leadbay_pin_contact`	Pin a contact as the priority on a company
`leadbay_unpin_contact`	Unpin a contact
`leadbay_update_contact`	Edit a contact's details (title, email, LinkedIn…)

Lenses & audience

Tool	Description
`leadbay_manage_lenses`	List, switch, rename/describe, or delete your lenses (delete is confirm-gated)
`leadbay_new_lens`	Create a named lens with sector / company-size (and optional location) criteria
`leadbay_adjust_audience`	Edit a lens's audience ("stop showing me companies over 50 employees"); pass `lensName` to edit a lens by name
`leadbay_extend_lens`	Fill your current lens with more leads on demand (subject to a daily refill quota)
`leadbay_refine_lead_targeting`	Refine the qualification prompt that scores your leads
`leadbay_answer_clarification`	Answer a clarification question Leadbay asked about your audience

Imports & campaigns

Tool	Description
`leadbay_import_leads`	Import a list of company domains
`leadbay_import_and_qualify`	Import a list and immediately qualify it
`leadbay_create_campaign`	Create a new campaign
`leadbay_add_leads_to_campaign`	Add leads to a campaign
`leadbay_remove_leads_from_campaign`	Remove leads from a campaign

Custom fields & qualification questions

Tool	Description
`leadbay_create_custom_field`	Create a custom CRM field (e.g. to preserve a source-system ID)
`leadbay_update_custom_field`	Rename or retype a custom field
`leadbay_delete_custom_field`	Delete a custom field (confirm-gated)
`leadbay_set_qualification_questions`	Modify the org's AI-agent qualification questions (max 5; removals confirm-gated)

Feedback

Tool	Description
`leadbay_send_feedback`	Send a message to the Leadbay team (same inbox as the in-app feedback form)

Advanced granular tools (gated by `LEADBAY_MCP_ADVANCED=1`)

Low-level, single-API-call tools for power users and integrations (leadbay_discover_leads, leadbay_get_lead_profile, leadbay_get_contacts, leadbay_list_lenses, …). Off by default; enable by setting LEADBAY_MCP_ADVANCED=1 in the MCP server's env. See packages/mcp/README.md for the full list.

How it works

The MCP server automatically uses your active lens (the last lens you used in Leadbay). Just call leadbay_pull_leads and it works — no lens configuration needed.

You can also manage lenses directly from chat: leadbay_manage_lenses lists them and switches/renames/deletes; leadbay_new_lens creates a named one with sector/size criteria; and leadbay_adjust_audience edits an existing lens (the active one, or any lens by name via lensName). Sector names resolve against the live taxonomy — leadbay_list_sectors surfaces the real labels.

leadbay_research_lead_by_id bundles multiple API calls (lead details + AI qualification + contacts) into a single response. If some data isn't available yet, it returns partial results instead of failing.

Configuration

Env var	Required	Description
`LEADBAY_TOKEN`	Yes	Local OAuth bearer credential (set by the installer)
`LEADBAY_REGION`	Yes	`us` or `fr`
`LEADBAY_MCP_WRITE`	No	Set to `0` to disable write tools (default: on since 0.3.0)
`LEADBAY_MCP_ADVANCED`	No	Set to `1` to expose granular tools (default: off)
`LEADBAY_BASE_URL`	No	Override API URL (for staging/dev)
`LEADBAY_TIMEOUT_MS`	No	Backstop deadline for one outbound request, in ms (default: 600000)

The full environment-variable reference (telemetry, mock mode, logging, timeouts) is in packages/mcp/README.md.

Workflows

The canonical inventory of what the MCP supports — supported / partial / planned / blocked-on-backend — is WORKFLOWS.md. Use it to triage incoming asks: find the row that matches, or add a new one. A small audit asserts every cited tool/prompt and test path is real, so the table can't silently drift.

Quick taste:

leadbay_pull_leads → leadbay_research_lead_by_id → leadbay_prepare_outreach   # discover & research
leadbay_pull_followups → leadbay_followups_map → leadbay_prepare_outreach     # travel/geo follow-ups
leadbay_import_leads → leadbay_bulk_qualify_leads                             # import & qualify

Requirements

Node.js 22+
A Leadbay account

Privacy Policy

The Leadbay MCP server accesses your Leadbay account data (leads, contacts, campaigns, notes) on your behalf through the Leadbay API, using a token you authorize via OAuth. It does not read your conversation history, Claude memory, or local files. Data handling is governed by the Leadbay privacy policy and terms of use.

Building from source

pnpm install

pnpm prompts:build

pnpm -r build

pnpm -r test

pnpm -r typecheck

Test tiers

Unit tests (packages/core/test/unit/) — error-code mapping, tool branches. Use mockHttp from test/harness.ts to stub node:https. No network required.
Integration tests (packages/core/test/integration/) — opt-in. Set LEADBAY_TEST_TOKEN and run pnpm test:smoke.
Audit tests (packages/mcp/test/audit/) — assert tool descriptions, routing blocks, and WORKFLOWS.md consistency at build time. Always run on CI.
Agent evaluations (evals/) — declarative journeys, isolated testing agents, and independent evidence verification. pnpm test:eval validates artifact contracts; it does not claim behavioral coverage.

See CLAUDE.md for the full contributor guide: tool structure, test conventions, build pipeline, and how to add a new tool.

Publishing

All releases are tag-driven — never run npm publish locally. GitHub Actions owns publishing.

Bump packages/mcp/package.json#version + add CHANGELOG entry, land PR.

git checkout main && git pull

git tag mcp-v0.x.0

git push origin mcp-v0.x.0

Watch the release workflow: preflight-npm → publish-mcp.

For dry runs: Actions → release → "Run workflow" → package: mcp, dry_run: true.

Full runbook (auth setup, failure modes, manual re-runs): RELEASE.md.

@leadbay/mcp

GitHub Actions

Model Context Protocol (MCP) server for Leadbay — AI lead discovery, qualification, and enrichment for Claude Desktop, Cursor, and Claude Code.

Devops Developer Tools

Add to Cursor Add to VS Code Run on PlugMCP

GitHub npm Website

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "leadbay-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@leadbay/[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y @leadbay/[email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add leadbay-mcp -- npx -y @leadbay/mcp@0.46.1

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "leadbay-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@leadbay/[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.46.1
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install @leadbay/mcp?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does @leadbay/mcp need an API key?

No required environment variable is listed on this record.

What transport does @leadbay/mcp use?

@leadbay/mcp runs locally over stdio.

When was @leadbay/mcp last checked?

Last checked 2026-10-28. Model Context Protocol (MCP) server for Leadbay — AI lead discovery, qualification, and enrichment for Claude Desktop, Cursor, and Claude Code.

From the publisher

Documentation

How Leadbay thinks (mental model for your agent)

Inbox, not a database. Each day your user logs back in, a fresh batch of leads is delivered. Batch size is paced by how many leads the user has actually acted on recently — some workflows produce a big stream of smaller prospects, others a narrow stream of bigger ones. Pulling more won't produce more; acting on leads does.
Two scoring layers. Every lead ships with a basic score (firmographic — already decent, usually correlates with AI). Roughly the top 10 of each batch are also AI-qualified (targeted web research + qualification questions → ai_agent_lead_score). Leads below the top 10 aren't worse — the system is saving resources. The agent can request deeper qualification (leadbay_bulk_qualify_leads) or contact enrichment (leadbay_enrich_titles) on any lead that looks worth it.
Daily rhythm. The agent works best as a daily check-in: pull fresh leads, skim the auto-qualified top, deepen 1-3 promising ones, propose outreach, then log what actually got sent via leadbay_report_outreach. If your host supports scheduling, set up a daily run.

For users

Get Leadbay MCP running inside your AI assistant in a couple of minutes. No coding required.

New to Leadbay? The friendly, screenshot-driven walkthrough — what a lens is, how scoring works, and the full MCP setup for every assistant — lives in the Leadbay user guide. This README is the technical companion.

No Leadbay account yet? Create one here first — you'll need it to sign in during setup.

Connect on the web (no install)

If you use Claude on the web, Claude Desktop, or ChatGPT, the fastest path is a custom connector — no terminal, no tokens to copy. Add one URL and sign in with your browser:

Name: Leadbay
URL: https://mcp.leadbay.app/mcp — one URL for every region (/fr/mcp remains a compatibility alias)
On ChatGPT, use https://mcp.leadbay.app/chatgpt/mcp instead. Same server, same sign-in, same leads — but the assistant cannot generate a top-up link or open your billing page there, because the OpenAI app directory does not allow an app to sell credits. Buy credits or change your plan in your Leadbay account instead.
On any other assistant (GitHub Copilot / VS Code, Goose, Cursor, …), use https://mcp.leadbay.app/apps/mcp. Same server, same sign-in, every region.
On ChatGPT and those assistants, today's leads open as the Lead Triage Board right in the chat, when the assistant can display it. Claude keeps its own widgets and artifacts on /mcp.

Install in Claude Desktop (one-click bundle)

Prefer a bundled desktop extension? Grab the one-click file.

1. Download the extension

👉 Download the latest Leadbay MCP for Claude (.dxt)

On the releases page, click the file ending in .dxt to download it.

2. Install it

Double-click the downloaded .dxt file. Claude opens and shows an install dialog — click Install, and you're done.

If the double-click doesn't open Claude, install it manually:

Open Claude and go to your profile → Settings → Extensions.
Open Advanced settings.
Choose Install extension… and select the .dxt file you downloaded.

3. Sign in

Claude will prompt you to connect Leadbay. Sign in with your Leadbay account and you're ready — just ask your agent for leads.

Using a local assistant?

Leadbay MCP also works with Claude Code, Claude Desktop, Cursor, and Codex. The universal installer sets everything up for you and lets you sign in with Leadbay.

Requires Node.js 22+. Then run:

npx -y -p @leadbay/mcp@latest installer

It opens in your browser where you click Sign in with Leadbay, then pick which assistants to connect. Works on macOS, Windows, and Linux.

To uninstall, run the same installer with --uninstall:

npx -y -p @leadbay/mcp@latest installer --uninstall

Ask for your first leads

Open a new conversation and describe the outcome — you never name a tool, just say what you want, the way you'd ask a colleague:

Show me today's leads and tell me which two are worth opening first.

A successful first reply is a ranked table of prospects, not a wall of text: each row has a fit score, a one-line why-it-fits, and the best contact to reach. Then keep going:

Research the top one — is it a fit for us?

Draft me an outreach email to them.

I just emailed them. Log it as outreach.

For developers

Everything below is for contributors and anyone running Leadbay MCP from source or wiring it into automation.

Install a local version with the custom installer

To run your local checkout (instead of the published package), first build it from source:

pnpm install
pnpm prompts:build
pnpm -r build

Then point the installer at your freshly built version with --local:

pnpm --filter @leadbay/mcp installer -- --local

All install methods

Every supported way to connect Leadbay MCP:

Method	Command / action	Platforms	Notes
Hosted connector (no install)	Add custom connector → `https://mcp.leadbay.app/mcp` (all regions)	Claude web / Desktop	Browser OAuth in-app. Nothing to install; auto-updates.
Hosted connector — ChatGPT	Add custom connector → `https://mcp.leadbay.app/chatgpt/mcp`	ChatGPT	Same server; the top-up and billing tools are not registered (OpenAI directory rule).
`.dxt` / `.mcpb` bundle	Download from Releases, double-click → Install	Claude Desktop	One-click desktop extension.
Guided installer (GUI)	`npx -y -p @leadbay/mcp@latest installer`	macOS, Windows, Linux	Browser wizard: sign in with Leadbay, pick clients. Works for everyone.
Local dev build	`pnpm --filter @leadbay/mcp installer -- --local`	macOS, Windows, Linux	Registers clients against your local build. OAuth automatic. Build from source first (above).
Claude Code plugin marketplace	`/plugin marketplace add leadbay/mcp` then `/plugin install leadbay@leadbay-mcp`	Claude Code	Registers the MCP server and installs auto-triggering skills.

What each installer writes per client

The GUI/CLI installers only touch clients that are actually installed on the machine:

Client	Installer behavior
Claude Code	Registers/removes `leadbay` with `claude mcp add/remove --scope user`
Claude Desktop	Writes/removes only the `mcpServers.leadbay` entry in `claude_desktop_config.json`
Cursor	Writes/removes only the `mcpServers.leadbay` entry in Cursor's MCP config
Codex	Writes/removes only the `[mcp_servers.leadbay]` block in `~/.codex/config.toml` and the Leadbay-managed shell export block

Claude Code plugin marketplace

/plugin marketplace add leadbay/mcp

/plugin install leadbay@leadbay-mcp

Uninstall

npx -y -p @leadbay/mcp@latest installer --uninstall

Tools

Reading tools (always on)

Discover & follow up

Tool	Description
`leadbay_pull_leads`	Pull today's fresh batch of scored, ranked leads. Records each one as seen, so it rotates out of tomorrow's batch
`leadbay_pull_followups`	Pull the leads that need a follow-up action. Saves the filter when you ask for one
`leadbay_account_status`	Check quota, credits, and account state
`leadbay_scan_portfolio_signals`	Scan your existing leads for a web signal in one pass ("which of my leads acquired a company since 2025?") — no quota burn. Saves the filter when you ask for one

Research a company

Tool	Description
`leadbay_research_lead_by_id`	Deep-dive research card for a known lead — details + AI qualification + contacts in one response. Records the lead as seen
`leadbay_research_lead_by_name_fuzzy`	Look up a lead by company name or domain when you don't have its ID. Records the lead it finds as seen
`leadbay_account_history`	Full history on one account — current AI signals + all notes + interaction timeline, in one call ("why has this account resurfaced?"). Records the lead as seen
`leadbay_prepare_outreach`	Build a personalized outreach brief for a lead. With enrichment on, it also orders the contact's details

Travel & field sales

Tool	Description
`leadbay_followups_map`	Geo-cluster your follow-ups on a map for travel planning. Saves the filter when you ask for one
`leadbay_tour_plan`	Build a visit itinerary for an upcoming trip to a city. Records the new leads it shows as seen

Campaigns

Tool	Description
`leadbay_list_campaigns`	List your existing campaigns
`leadbay_campaign_progression`	Show a campaign's funnel metrics
`leadbay_campaign_call_sheet`	Pull the call sheet for a campaign

Lenses, audience & qualification

Tool	Description
`leadbay_list_sectors`	List the real sector taxonomy labels — so you (and the agent) name sectors correctly, no guessing
`leadbay_list_previously_enriched_titles`	Recall the job titles previously enriched by the org (use before `leadbay_enrich_titles`)
`leadbay_list_lens_seed_candidates`	Read-only discovery surface for building a bigger lens
`leadbay_get_qualification_questions`	Retrieve the org's AI-agent qualification questions (how leads are scored)
`leadbay_get_lead_custom_fields`	Retrieve the custom-field values stored on one lead. Records the lead as seen
`leadbay_list_mappable_fields`	List the CRM fields you can map an import onto. Given sample rows, it uploads them to get the backend's mapping hints

Imports & jobs

Tool	Description
`leadbay_import_status`	Status of a running import job
`leadbay_qualify_status`	Status of a running qualification job
`leadbay_bulk_enrich_status`	Status of a running enrichment job
`leadbay_resolve_import_rows`	Map imported rows back to their lead IDs

Team, billing & product signals

Tool	Description
`leadbay_team_activity`	Manager-facing per-rep leaderboard + activity trend (non-admins are scoped to themselves)
`leadbay_create_topup_link`	Generate a Stripe top-up link (you pay in your browser — nothing is charged automatically)
`leadbay_open_billing_portal`	Open the billing portal
`leadbay_acknowledge_notification`	Clear a terminal bulk-job notification so it stops resurfacing
`leadbay_report_friction`	Report a problem to the Leadbay team — asks you first, and shows you what was sent (no account change)
`leadbay_get_artifact_runtime`	Fetch the headless view-models the agent uses to build an interactive HTML artifact

Write actions (on by default since 0.3.0; set `LEADBAY_MCP_WRITE=0` to disable)

These take action on your account. Every action is one you could take yourself in the app — there's nothing destructive at the platform level, and deletes are confirm-gated.

Qualify & enrich

Tool	Description
`leadbay_bulk_qualify_leads`	Trigger AI qualification on a batch of leads
`leadbay_enrich_titles`	Enrich contacts by job title
`leadbay_enrich_contacts`	Enrich one specific person (email / phone) — the contact you name, not a job title

Outreach & activity

Tool	Description
`leadbay_report_outreach`	Log an outreach action (call, email, meeting) — required after every contact
`leadbay_add_note`	Add a note to a lead
`leadbay_like_lead`	Mark a lead as liked — teaches your taste profile
`leadbay_dislike_lead`	Mark a lead as disliked — teaches your taste profile

Contacts

Tool	Description
`leadbay_add_contact`	Add a person to a company (name + optional LinkedIn / title / email / phone)
`leadbay_remove_contact`	Remove a contact you added
`leadbay_pin_contact`	Pin a contact as the priority on a company
`leadbay_unpin_contact`	Unpin a contact
`leadbay_update_contact`	Edit a contact's details (title, email, LinkedIn…)

Lenses & audience

Tool	Description
`leadbay_manage_lenses`	List, switch, rename/describe, or delete your lenses (delete is confirm-gated)
`leadbay_new_lens`	Create a named lens with sector / company-size (and optional location) criteria
`leadbay_adjust_audience`	Edit a lens's audience ("stop showing me companies over 50 employees"); pass `lensName` to edit a lens by name
`leadbay_extend_lens`	Fill your current lens with more leads on demand (subject to a daily refill quota)
`leadbay_refine_lead_targeting`	Refine the qualification prompt that scores your leads
`leadbay_answer_clarification`	Answer a clarification question Leadbay asked about your audience

Imports & campaigns

Tool	Description
`leadbay_import_leads`	Import a list of company domains
`leadbay_import_and_qualify`	Import a list and immediately qualify it
`leadbay_create_campaign`	Create a new campaign
`leadbay_add_leads_to_campaign`	Add leads to a campaign
`leadbay_remove_leads_from_campaign`	Remove leads from a campaign

Custom fields & qualification questions

Tool	Description
`leadbay_create_custom_field`	Create a custom CRM field (e.g. to preserve a source-system ID)
`leadbay_update_custom_field`	Rename or retype a custom field
`leadbay_delete_custom_field`	Delete a custom field (confirm-gated)
`leadbay_set_qualification_questions`	Modify the org's AI-agent qualification questions (max 5; removals confirm-gated)

Feedback

Tool	Description
`leadbay_send_feedback`	Send a message to the Leadbay team (same inbox as the in-app feedback form)

Advanced granular tools (gated by `LEADBAY_MCP_ADVANCED=1`)

How it works

The MCP server automatically uses your active lens (the last lens you used in Leadbay). Just call leadbay_pull_leads and it works — no lens configuration needed.

Configuration

Env var	Required	Description
`LEADBAY_TOKEN`	Yes	Local OAuth bearer credential (set by the installer)
`LEADBAY_REGION`	Yes	`us` or `fr`
`LEADBAY_MCP_WRITE`	No	Set to `0` to disable write tools (default: on since 0.3.0)
`LEADBAY_MCP_ADVANCED`	No	Set to `1` to expose granular tools (default: off)
`LEADBAY_BASE_URL`	No	Override API URL (for staging/dev)
`LEADBAY_TIMEOUT_MS`	No	Backstop deadline for one outbound request, in ms (default: 600000)

The full environment-variable reference (telemetry, mock mode, logging, timeouts) is in packages/mcp/README.md.

Workflows

Quick taste:

leadbay_pull_leads → leadbay_research_lead_by_id → leadbay_prepare_outreach   # discover & research
leadbay_pull_followups → leadbay_followups_map → leadbay_prepare_outreach     # travel/geo follow-ups
leadbay_import_leads → leadbay_bulk_qualify_leads                             # import & qualify

Requirements

Node.js 22+
A Leadbay account

Privacy Policy

Building from source

pnpm install

pnpm prompts:build

pnpm -r build

pnpm -r test

pnpm -r typecheck

Test tiers

Unit tests (packages/core/test/unit/) — error-code mapping, tool branches. Use mockHttp from test/harness.ts to stub node:https. No network required.
Integration tests (packages/core/test/integration/) — opt-in. Set LEADBAY_TEST_TOKEN and run pnpm test:smoke.
Audit tests (packages/mcp/test/audit/) — assert tool descriptions, routing blocks, and WORKFLOWS.md consistency at build time. Always run on CI.
Agent evaluations (evals/) — declarative journeys, isolated testing agents, and independent evidence verification. pnpm test:eval validates artifact contracts; it does not claim behavioral coverage.

See CLAUDE.md for the full contributor guide: tool structure, test conventions, build pipeline, and how to add a new tool.

Publishing

All releases are tag-driven — never run npm publish locally. GitHub Actions owns publishing.

Bump packages/mcp/package.json#version + add CHANGELOG entry, land PR.

git checkout main && git pull

git tag mcp-v0.x.0

git push origin mcp-v0.x.0

Watch the release workflow: preflight-npm → publish-mcp.

For dry runs: Actions → release → "Run workflow" → package: mcp, dry_run: true.

Full runbook (auth setup, failure modes, manual re-runs): RELEASE.md.

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install @leadbay/mcp?

Does @leadbay/mcp need an API key?

What transport does @leadbay/mcp use?

When was @leadbay/mcp last checked?

Documentation

How Leadbay thinks (mental model for your agent)

For users

Connect on the web (no install)

Install in Claude Desktop (one-click bundle)

Using a local assistant?

Ask for your first leads

For developers

Install a local version with the custom installer

All install methods

What each installer writes per client

Claude Code plugin marketplace

Uninstall

Tools

Reading tools (always on)

Write actions (on by default since 0.3.0; set LEADBAY_MCP_WRITE=0 to disable)

Advanced granular tools (gated by LEADBAY_MCP_ADVANCED=1)

How it works

Configuration

Workflows

Requirements

Privacy Policy

Building from source

Test tiers

Publishing

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install @leadbay/mcp?

Does @leadbay/mcp need an API key?

What transport does @leadbay/mcp use?

When was @leadbay/mcp last checked?

Documentation

How Leadbay thinks (mental model for your agent)

For users

Connect on the web (no install)

Install in Claude Desktop (one-click bundle)

Using a local assistant?

Ask for your first leads

For developers

Install a local version with the custom installer

All install methods

What each installer writes per client

Claude Code plugin marketplace

Uninstall

Tools

Reading tools (always on)

Write actions (on by default since 0.3.0; set LEADBAY_MCP_WRITE=0 to disable)

Advanced granular tools (gated by LEADBAY_MCP_ADVANCED=1)

How it works

Configuration

Workflows

Requirements

Privacy Policy

Building from source

Test tiers

Publishing

Write actions (on by default since 0.3.0; set `LEADBAY_MCP_WRITE=0` to disable)

Advanced granular tools (gated by `LEADBAY_MCP_ADVANCED=1`)

Write actions (on by default since 0.3.0; set `LEADBAY_MCP_WRITE=0` to disable)

Advanced granular tools (gated by `LEADBAY_MCP_ADVANCED=1`)