Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y [email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
claude mcp add langflow-mcp-server -- npx -y langflow-mcp-server@4.13.5รันในเทอร์มินัล
{ "mcpServers": { "langflow-mcp-server": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
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.
เปิดA Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to Langflow workflow automation platform.
langflow-mcp-server serves as a bridge between Langflow's workflow automation platform and AI models, enabling them to understand and work with Langflow flows effectively.
API Compatibility: This server targets Langflow API version 1.13.0 for its existing tools, the latest stable release checked on 2026-10-25 (released 2026-10-22, source commit 63082cf9a9c0e5bbeda12bba0aa9e0b05ffffe6a). Review of the 1.12.6 to 1.13.0 changes identified required policy, team-membership and user-management updates. This is a bounded source-contract review, supported by local regression and installed-package tests; a live end-to-end run against Langflow 1.13.0 has not been performed. New upstream connection, trigger, migration-administration and deployment-snapshot APIs are not exposed as tools.
Policy replacement requires the current revision and all six policy lists, including approved_integration_provider_ids and blocked_integration_action_keys. Read the current bundle before replacing it; an explicit empty list clears that policy set. Manual team-membership creation accepts only source: "manual" or an omitted source. Password reset requires an interactive Langflow login and is unavailable through this client's API-key authentication; its retained tool returns an actionable error without sending the password. The exported deleteUser method returns the deletion-started response and request_id; acceptance does not mean deletion has completed. Upstream authorization, policy, storage-unavailability and migration-pause errors remain errors.
Versioning: From 4.10.0 onward, the npm minor version mirrors the targeted Langflow minor: langflow-mcp-server@4.<langflow_minor>.x targets Langflow 1.<langflow_minor>.x (for example, 4.13.x targets Langflow 1.13.x). The patch component is used for fixes within the same Langflow minor.
Langflow 1.13.0 returns the newest 100 sessions or messages by default, with a maximum of 200 per request; an omitted or zero limit selects the default. Both MCP modes expose limit for normal/shared sessions and messages, plus offset and display order for message history. Upstream now supports session-list offsets, but these MCP tools do not yet expose them, so session enumeration remains limited to the first page. Message-ID lookup scans history pages within the configured Langflow timeout. Concurrent history changes can shift offset-based pages; these reads are not snapshots. MCP server configuration responses mask stored credentials as ********; these responses are not credential backups. Counted MCP discovery can return HTTP 429 when busy, and attachment/execution requests remain subject to upstream scope and policy checks.
Audit-log event filters and provider/model/store list filters retain repeated query keys. Regression tests cover these requests, history controls, policy replacement, changed user/team contracts and upstream errors. Installed-tarball smoke tests exercise both MCP modes over stdio and HTTP with local fixtures, including preservation of nonempty integration policies.
Consolidated Tools Mode is an architecture that groups the 236 individual tools into 29 action-based meta-tools. This significantly reduces token usage and improves AI assistant context management.
To enable consolidated mode:
LANGFLOW_CONSOLIDATED_TOOLS=true
Consolidated tools:
flow - All flow operations (list, get, create, update, delete, download, upload, replace, expand, batch, public, note_translations)flow_execution - Run flows (run, run_advanced, run_session, webhook, process, predict)flow_version - Flow versions and lifecycle events (list, create, get, delete, activate, get_events, create_event)build - Build operations (start, status, cancel, public build lifecycle, vertices)workflow - Run and manage v2 workflows (run with request-level globals, get_result, stop, plus HITL/public execution)agentic - Agentic assistant + sandbox (assist, assist_stream, assist_run, check_config, execute, get_file, reset_session)folder - Folder management (list, get, create, update, delete, download, upload)project - Project management (list, get, create, update, upsert, delete, download, upload)variable - Variable operations (list, create, update, delete, detect)knowledge_base - Knowledge base management (list, get, delete, bulk_delete, upload, create, preview/list chunks, ingest, cancel_ingest, test_connection, list_connectors, ingest_folder, ingest_connector, metadata_keys, list_runs, get_run)memory - Memory bases (create, list, get, list_sessions, list_messages, update, delete, flush, mismatch, regenerate) — experimental Langflow APIfile - Flow-scoped file operations (list, upload, download, delete, get_image)file_v2 - User-scoped v2 files (list, upload, get, rename, delete, delete_all, batch_download, batch_delete)monitor - Monitoring (builds, messages, sessions, transactions, job_queue)trace - Execution traces (list, get, delete, delete_by_flow)model - Models and providers (list, providers, provider descriptors, enabled, default get/set/delete, mapping, validate, options)governance - Langflow 1.12.x provider, catalog, and policy-bundle administrationauthz - RBAC authorization (roles, role assignments, teams, shares, audit, my permissions)user - User management (list, get_current, update, reset_password, create)auth - Authentication (login, auto_login, logout, refresh, api keys, save_store_key)store - Component store (list, get, tags, likes, save_api_key, create, like, update_custom)registration - User registration (get, register)validation - Code/prompt validation (code, prompt)mcp_server - MCP server management (list, get, create, update, delete)mcp_project - MCP project config/install (get/update config, get_installed, install, composer_url)extension - Langflow extensions (reload, events)response - OpenAI-compatible responses (create)system - System info (health, version, logs, pictures, voices, session, webhook_events, health_check, healthz)a2a - A2A (Agent-to-Agent) protocol (list_agents, agent_card, jsonrpc)It provides structured access to:
# Install from npm
npm install -g langflow-mcp-server
# OR clone the repository
git clone https://github.com/nobrainer-tech/langflow-mcp.git
cd langflow-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Configure environment
cp .env.example .env
# Edit .env with your Langflow instance URL and API key
Edit .env file:
LANGFLOW_BASE_URL=http://localhost:7860
LANGFLOW_API_KEY=your-api-key-here
MCP_MODE=stdio
LOG_LEVEL=info
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"langflow": {
"command": "npx",
"args": ["-y", "langflow-mcp-server"],
"env": {
"LANGFLOW_BASE_URL": "http://localhost:7860",
"LANGFLOW_API_KEY": "your-api-key-here",
"LANGFLOW_CONSOLIDATED_TOOLS": "true",
"MCP_MODE": "stdio",
"LOG_LEVEL": "error"
}
}
}
}
Alternative (local installation):
{
"mcpServers": {
"langflow": {
"command": "node",
"args": ["/absolute/path/to/langflow-mcp/dist/mcp/index.js"],
"env": {
"LANGFLOW_BASE_URL": "http://localhost:7860",
"LANGFLOW_API_KEY": "your-api-key-here",
"MCP_MODE": "stdio",
"LOG_LEVEL": "error"
}
}
}
}
Restart Claude Desktop after updating configuration.
The server supports both standard MCP transports: local stdio and remote
Streamable HTTP. MCP clients use the same tool and schema surface regardless
of transport. Use stdio when the host can launch a local process; use HTTP
when the server runs as a separately deployed service.
codex mcp add langflow \
--env LANGFLOW_BASE_URL=http://localhost:7860 \
--env LANGFLOW_API_KEY=your-api-key-here \
-- npx -y langflow-mcp-server
claude mcp add langflow \
-e LANGFLOW_BASE_URL=http://localhost:7860 \
-e LANGFLOW_API_KEY=your-api-key-here \
-- npx -y langflow-mcp-server
Start the server with an explicit bearer token when binding outside the local
machine. HOST=127.0.0.1 is the secure default; use HOST=0.0.0.0 only with
authentication and a TLS-terminating reverse proxy.
MCP_MODE=http \
HOST=0.0.0.0 \
PORT=3000 \
AUTH_TOKEN=replace-with-a-long-random-token \
LANGFLOW_BASE_URL=https://langflow.example.com \
LANGFLOW_API_KEY=your-api-key-here \
npx -y langflow-mcp-server
The MCP endpoint is https://your-host.example/mcp; the health endpoint is
https://your-host.example/health. For browser-based callers, set
MCP_ALLOWED_ORIGINS to a comma-separated list of exact HTTPS origins. Wildcard
origins are rejected.
Codex CLI can keep the bearer token in an environment variable:
export LANGFLOW_MCP_TOKEN='set-this-in-your-shell'
codex mcp add langflow-remote \
--url https://your-host.example/mcp \
--bearer-token-env-var LANGFLOW_MCP_TOKEN
The environment variable must be present whenever Codex starts or reconnects to this server.
Claude Code accepts the same Streamable HTTP endpoint:
export LANGFLOW_MCP_TOKEN='set-this-in-your-shell'
claude mcp add --transport http --scope user \
--header "Authorization: Bearer ${LANGFLOW_MCP_TOKEN}" \
langflow-remote https://your-host.example/mcp
This stores the header in the Claude MCP configuration; keep that configuration
outside source control. Hosts such as Cloud Code, Gemini
clients, and other MCP-compatible tools can use the same /mcp endpoint when
they support Streamable HTTP; their configuration syntax is host-specific and
has not been claimed as an end-to-end test in this repository.
The MCP server can be run in a Docker container for easier deployment and isolation.
# Clone the repository
git clone https://github.com/nobrainer-tech/langflow-mcp.git
cd langflow-mcp
# Create .env file with your configuration
cp .env.example .env
# Edit .env with your Langflow instance URL and API key
# Build and run with docker-compose
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the server
docker-compose down
# Build the image
docker build -t langflow-mcp-server:latest .
# Run in stdio mode (for Claude Desktop)
docker run -it --rm \
-e LANGFLOW_BASE_URL=http://localhost:7860 \
-e LANGFLOW_API_KEY=your-api-key \
langflow-mcp-server:latest
# Run in HTTP mode (for remote access)
docker run -d \
-p 3000:3000 \
-e MCP_MODE=http \
-e HOST=0.0.0.0 \
-e PORT=3000 \
-e AUTH_TOKEN=your-secure-token \
-e MCP_ALLOWED_ORIGINS=https://your-client.example \
-e LANGFLOW_BASE_URL=http://langflow:7860 \
-e LANGFLOW_API_KEY=your-api-key \
langflow-mcp-server:latest
The included docker-compose.yml supports both stdio and HTTP modes:
# STDIO mode (default)
environment:
- MCP_MODE=stdio
- LANGFLOW_BASE_URL=http://localhost:7860
- LANGFLOW_API_KEY=your-key
# HTTP mode
environment:
- MCP_MODE=http
- PORT=3000
- AUTH_TOKEN=your-secure-token
- MCP_ALLOWED_ORIGINS=https://your-client.example
Once connected, Claude can use:
Note: Raw Langflow transport endpoints (
/api/mcp/*) and doc-rendering endpoints (/docs,/redoc,/openapi.json) are intentionally not exposed as tools — they are protocol/transport surfaces, not data operations.
create_flow - Create a new Langflow flowlist_flows - List all flows with pagination and filteringget_flow - Get details of a specific flow by IDupdate_flow - Update an existing flowdelete_flow - Delete a single flowdelete_flows - Delete multiple flows at oncereplace_flow - Replace a flow's full definitionexpand_flows - Expand flows with embedded component dataupload_flow - Upload a flow from JSON datadownload_flows - Download multiple flows as JSON exportget_basic_examples - Get pre-built example flowsbatch_create_flows - Create multiple flows in one operationget_public_flow - Get a public flow without authenticationrun_flow - Execute a flow with input configuration (supports streaming)run_flow_advanced - Advanced flow execution with full controlrun_flow_session - Execute a flow within a session contexttrigger_webhook - Trigger a flow via webhook endpointget_webhook_events - Get webhook trigger events for a flowprocess_flow - Legacy process endpoint for flowspredict_flow - Legacy predict endpoint for flowslist_flow_versions - List versions of a flowcreate_flow_version - Create a new flow versionget_flow_version - Get a specific flow versiondelete_flow_version - Delete a flow versionactivate_flow_version - Activate a specific flow versionget_flow_events - Get lifecycle events for a flowcreate_flow_event - Create a lifecycle event for a flowbuild_flow - Build/compile a flow and return job_id for async executionget_build_status - Poll build status and events for a specific jobcancel_build - Cancel a running build jobbuild_public_flow - Build a public flow without authenticationget_public_build_events - Get events for a public build jobcancel_public_build - Cancel a public build jobget_task_status - Get status of an async taskbuild_vertices - Get vertex build order for a flowstream_vertex_build - Stream real-time build events for a vertexrun_workflow - Run a v2 workflowget_workflow_result - Get the result of a workflow runstop_workflow - Stop a running workflowlist_pending_workflows - List pending HITL requests for a flowget_workflow_events - Re-attach to a workflow job event streamresume_workflow - Resume a workflow with a request ID and optional decisionrun_public_workflow - Run a public stream-only workflowagentic_assist - Get agentic assistance for a flow componentagentic_assist_stream - Get streaming agentic assistance for a flow componentagentic_assist_run - Run the assistant headlessly and persist flow changesagentic_check_config - Check whether agentic features are configuredagentic_execute - Execute an agentic flow by namecreate_response - Create an OpenAI-compatible responseget_session - Get a response/conversation sessionlist_folders - List all folders with paginationcreate_folder - Create a new folderget_folder - Get folder details by IDupdate_folder - Update folder name, description, or parentdelete_folder - Delete a folderdownload_folder - Download entire folder as archiveupload_folder - Upload folder from archivelist_projects - List all projects with paginationcreate_project - Create a new projectget_project - Get project details by IDupdate_project - Update project name or descriptionupsert_project - Create or update a project at a caller-supplied IDdelete_project - Delete a projectupload_project - Upload a project from JSON datadownload_project - Download a project as JSON exportlist_variables - List all global variablescreate_variable - Create a new variableupdate_variable - Update variable propertiesdelete_variable - Delete a variabledetect_variables - Detect variables referenced in a value/templatelist_knowledge_bases - List all available knowledge baseslist_knowledge_bases_detailed - List knowledge bases with detailed metadataget_knowledge_base - Get detailed information about a specific knowledge basecreate_knowledge_base - Create a new knowledge basedelete_knowledge_base - Delete a specific knowledge basebulk_delete_knowledge_bases - Delete multiple knowledge bases at onceupload_knowledge_base - Upload a file to create/update a knowledge basepreview_knowledge_base_chunks - Preview how a document will be chunkedlist_knowledge_base_chunks - List stored chunks for a knowledge baseingest_knowledge_base - Ingest documents into a knowledge basecancel_knowledge_base_ingest - Cancel an in-progress ingest jobupload_file - Upload a file to a specific flowdownload_file - Download a file from a flowlist_files - List all files in a flowdelete_file - Delete a file from a flowget_file_image - Get an image file from a flowlist_files_v2 - List all user-scoped v2 filesupload_file_v2 - Upload a v2 fileget_file_v2 - Get v2 file metadata or contentrename_file_v2 - Rename a v2 filedelete_file_v2 - Delete a v2 filedelete_all_files_v2 - Delete all v2 filesbatch_download_files_v2 - Download multiple v2 filesbatch_delete_files_v2 - Delete multiple v2 fileslist_components - List all available Langflow componentscreate_custom_component - Create a new custom componentupdate_custom_component - Update an existing custom componentget_monitor_builds - Get build execution history for a flowget_monitor_messages - Query a message-history window with filtering, limit, offset, and display orderget_monitor_message - Look up a message across history pages within the configured timeoutupdate_monitor_message - Update a stored messageget_monitor_sessions - List the newest session IDs (limit: default 100, maximum 200)get_monitor_session_messages - Query a session's message-history window with limit, offset, and display ordermigrate_monitor_session - Migrate messages between sessionsget_monitor_transactions - List transaction logs for a flowdelete_monitor_builds - Delete build history for a flowdelete_monitor_messages - Delete multiple messages by IDdelete_monitor_session_messages - Delete all messages for a sessiondelete_monitor_sessions - Delete chat sessionslist_traces - List execution traces with filtersget_trace - Get a specific execution tracedelete_trace - Delete a specific tracedelete_traces - Delete all traces for a flowget_shared_messages - Query a shared message-history window with limit, offset, and display orderget_shared_sessions - List the newest shared session IDs (limit: default 100, maximum 200)update_shared_message - Update a shared messagemigrate_shared_session - Migrate a shared sessiondelete_shared_session - Delete a shared sessionlist_models - List available modelslist_model_providers - List all model providerslist_model_provider_descriptors - List providers with stable IDs and display nameslist_enabled_providers - List enabled providerslist_enabled_models - List enabled modelsset_enabled_models - Enable/disable modelsget_default_model - Get the default model for a typeset_default_model - Set the default model for a typedelete_default_model - Remove the default model for a typeget_provider_variable_mapping - Get provider-to-variable mappingvalidate_model_provider - Validate provider credentialsget_language_model_options - Get language model optionsget_embedding_model_options - Get embedding model optionslist_users - List all users (admin only)get_current_user - Get current authenticated user infoupdate_user - Update user profile informationreset_user_password - Returns an interactive-login requirement; password changes are unavailable with API-key authenticationcreate_user - Create a new user (admin only)list_api_keys - List all API keys for the usercreate_api_key - Create a new API keydelete_api_key - Delete an API keylogin - Authenticate with username and passwordauto_login - Auto-login with stored credentialsrefresh_token - Refresh authentication tokenlogout - Logout and invalidate sessionget_registration - Check whether registration is enabledregister_user - Register a new user accountcheck_store - Check if component store is enabledcheck_store_api_key - Validate a store API keysave_store_api_key - Save a store API keylist_store_components - Browse available components in the storeget_store_component - Get details of a store componentcreate_store_component - Publish a component to the storelike_store_component - Like a store componentlist_store_tags - List all component tags in the storeget_user_likes - Get components liked by uservalidate_code - Validate Python code for custom componentsvalidate_prompt - Validate prompt template syntaxlist_mcp_servers - List MCP servers registered with Langflowget_mcp_server - Get an MCP server by namecreate_mcp_server - Create an MCP serverupdate_mcp_server - Update an MCP serverdelete_mcp_server - Delete an MCP serverget_mcp_project_config - Get MCP config for a projectupdate_mcp_project_config - Update MCP config for a projectget_mcp_project_installed - Get installed MCP clients for a projectinstall_mcp_project - Install MCP for a project into a clientget_mcp_project_composer_url - Get the MCP composer URL for a projectlist_starter_projects - List available starter templateslist_profile_pictures - List available profile picturesget_profile_picture - Get a specific profile picturelist_elevenlabs_voices - List ElevenLabs text-to-speech voicesget_version - Get Langflow API version informationhealth_check - Check Langflow instance health statusget_health_check - Get a detailed health-check reportget_healthz - Get the Kubernetes-style readiness reportget_logs - Retrieve system logs (supports streaming)list_authz_roles, get_authz_role, create_authz_role, update_authz_role, delete_authz_role - Manage roleslist_authz_role_assignments, create_authz_role_assignment, delete_authz_role_assignment - Manage role assignmentslist_authz_teams, get_authz_team, create_authz_team, update_authz_team, delete_authz_team - Manage teamslist_authz_team_members, add_authz_team_member, remove_authz_team_member - Manage team memberslist_authz_shares, get_authz_share, create_authz_share, update_authz_share, delete_authz_share - Manage resource sharesget_authz_audit - Query the authorization audit log (superuser)get_my_permissions - Get the caller's effective permissionscreate_memory_base, list_memory_bases, get_memory_base - Manage memory baseslist_memory_base_sessions, list_memory_base_messages - Inspect tracked sessions/messagesupdate_memory_base, delete_memory_base - Update/delete a memory baseflush_memory_base, check_memory_base_mismatch, regenerate_memory_base - Lifecycle operationstest_knowledge_base_connection - Test a vector backend connectionlist_knowledge_base_connectors - List available ingestion connectorsingest_knowledge_base_folder, ingest_knowledge_base_connector - Ingest from a server folder or connectorget_knowledge_base_metadata_keys - List distinct metadata keys/valueslist_knowledge_base_runs, get_knowledge_base_run - Inspect ingestion runsreload_extension_bundle - Reload an extension bundle (requires server-side flag)get_extension_events - Poll extension events for the current userget_agentic_file - Read a file from the per-user agentic sandboxreset_agentic_session - Reset agentic session/sandbox stateget_flow_note_translations - Get localized note-node translations for a flowget_job_queue_metrics - Job-queue metrics snapshot (superuser)get_model_provider_policy, replace_model_provider_policy - Read or replace the install-wide approved-provider policyget_catalog_component_policy, replace_catalog_component_policy - Read or replace blocked component keysget_catalog_template_policy, replace_catalog_template_policy - Read or replace blocked template keysget_catalog_policy_usage, get_catalog_policy_usage_flows - Inspect component usage across flowsget_policy_bundle, replace_policy_bundle - Read or atomically replace the combined governance policylist_policy_bundle_history, rollback_policy_bundle - Inspect or roll back policy revisionsPolicy replacement operations are superuser-only and use complete sets. Read the current policy revision before writing so optimistic concurrency conflicts are handled explicitly.
The v2 workflow runner (
run_workflow/workflowactionrun) also accepts request-levelglobals, the preferred replacement for the deprecatedX-LANGFLOW-GLOBAL-VAR-*headers.
list_a2a_agents - List available A2A (Agent-to-Agent) agentsget_a2a_agent_card - Get a flow's A2A agent card (.well-known/agent-card.json)invoke_a2a_jsonrpc - Invoke a flow via the A2A JSON-RPC endpoint (passthrough envelope)A2A endpoints require server-side enablement (
LANGFLOW_A2A_ENABLED); otherwise requests surface as a thrownFailed to ...error.
list_pending_workflows - List pending human-in-the-loop requests for a required flow_idget_workflow_events - Re-attach to a workflow job event stream by job IDresume_workflow - Resume a paused HITL workflow with request_id and an optional decisionrun_public_workflow - Run a public (unauthenticated-eligible) workflowThe
get_workflow_eventsandrun_public_workflowendpoints return server-sent-event streams; the initial payload is captured but streaming is not incrementally surfaced.
Langflow 1.11.x adds external trusted-JWT / JIT-provisioning authentication. This is
controlled entirely by the Langflow server environment and adds no MCP tools:
EXTERNAL_AUTH_ENABLED, EXTERNAL_AUTH_TOKEN_HEADER/EXTERNAL_AUTH_TOKEN_COOKIE,
EXTERNAL_AUTH_JWKS_URL, EXTERNAL_AUTH_ISSUER/EXTERNAL_AUTH_AUDIENCE/EXTERNAL_AUTH_ALGORITHMS,
EXTERNAL_AUTH_*_CLAIM, and EXTERNAL_AUTH_ACCESS_CEILING_*. The MCP client keeps using its
API key / Bearer token as before.
// Create a new flow
create_flow({
name: "My Automation Flow",
description: "A flow that processes data"
})
// List all flows
list_flows({
page: 1,
size: 50
})
// Get flow details
get_flow({
flow_id: "flow-uuid-here"
})
// Update a flow
update_flow({
flow_id: "flow-uuid-here",
name: "Updated Flow Name"
})
// Execute a flow
run_flow({
flow_id_or_name: "my-flow-name",
input_request: {
input_value: "Hello World",
output_type: "chat",
input_type: "chat"
},
stream: false
})
// Trigger via webhook
trigger_webhook({
flow_id_or_name: "my-flow",
input_request: {
input_value: "Process this data"
}
})
// Build a flow (compile/validate)
build_flow({
flow_id: "flow-uuid-here",
log_builds: true,
event_delivery: "polling"
})
// Check build status
get_build_status({
job_id: "job-uuid-from-build",
event_delivery: "polling"
})
// List knowledge bases (RAG)
list_knowledge_bases()
// Get knowledge base details
get_knowledge_base({
kb_name: "my-documents"
})
// Create a folder
create_folder({
name: "My Flows",
description: "Organized flows"
})
// Create a project
create_project({
name: "My Project",
description: "Project description"
})
// Manage variables
create_variable({
name: "API_KEY",
value: "secret-key",
type: "string"
})
// Get basic examples
get_basic_examples()
// List all components
list_components()
Use Node.js 22.12 or newer in the 22.x line, or Node.js 24.x, for the Vitest 5 toolchain. The published server still supports Node.js 20 and newer. CI tests the toolchain on Node.js 22/24 and the installed package on Node.js 20/22/24.
# Build
npm run build
# Run in development mode
npm run dev
# Run tests
npm test
# Type checking
npm run typecheck
# HTTP development server with automatic TypeScript reload
npm run dev:http
langflow-mcp/
├── src/
│ ├── mcp/
│ │ ├── index.ts # MCP server entry point
│ │ ├── http.ts # Streamable HTTP transport
│ │ ├── server.ts # MCP server implementation
│ │ └── tools.ts # Tool definitions
│ ├── services/
│ │ └── langflow-client.ts # Langflow API client
│ ├── types/
│ │ └── index.ts # TypeScript types
│ └── utils/
│ └── logger.ts # Logging utility
├── .env.example # Example configuration
├── package.json
├── tsconfig.json
└── README.md
Developed with NoBrainer.Tech Flow for scoped implementation, independent reviews and release verification.
This project is inspired by and follows the structure of n8n-mcp by Romuald Czlonkowski. Special thanks to the n8n-mcp project for the excellent MCP server architecture and implementation patterns.
MIT License - see LICENSE for details.
Contributions are welcome! Please:
npm test)Release through .github/workflows/publish.yml on GitHub-hosted runners. The npm Trusted Publisher must use owner nobrainer-tech, repository langflow-mcp, workflow publish.yml, an empty environment and permission to run npm publish. No stored npm write token is required.
After reviewed changes are merged, push a new stable tag matching package.json and the lockfile. The workflow checks that the tag belongs to master, runs typecheck, tests, packaged MCP smoke and security audit, then publishes and verifies the exact npm commit and provenance before creating the GitHub Release. Existing tags must not be moved.
The provenance check binds the attestation's package, tarball SHA-512 digest, source repository and commit. It does not perform cryptographic verification of Sigstore signatures.
For tags created from 4.12.1 onward, recover an interrupted release by running the workflow at that exact tag (for example gh workflow run publish.yml --ref v4.12.1). This keeps the build source aligned with GitHub's provenance identity. An already-published version is accepted only when its commit and provenance match; it is never overwritten.
Built with ❤️ for the Langflow community
Integration for Langflow API 1.13.2 via Model Context Protocol (MCP)
{ "mcpServers": { "langflow-mcp-server": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Langflow ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-13 Integration for Langflow API 1.13.2 via Model Context Protocol (MCP)