Dsh MCP Bridge

dsh-mcp-bridge

Install six curated MCP servers into DSH in one command — and find out which of them actually work on your machine.

When you need this

• You want your DSH agent to have MCP tools (browser automation, session memory, file access) without hand-writing six configs and getting the quoting wrong
• A server will not start and you cannot tell whether it is the config, the package or your network
• You want a list that says which servers are genuinely reachable, rather than another copy of the upstream docs

Every curated server is started, handshaken and its tool count checked in CI — everything answers with 13 tools, memory with 9, filesystem with 14.

One install gives your dsh agent a set of MCP servers that are started and queried on every push — not a raw YAML you have to figure out. Every curated server has a machine-readable definition in servers/, and scripts/verify-servers.mjs checks each one's connectivity, so "verified" is a CI-guaranteed claim, not marketing.

Tools appear to the model as mcp__<serverName>__<toolName> (same server-qualified shape as Claude Code / Codex). The bridge itself is DSH's built-in @deepseek-ai/dsh-mcp-client: stdio + streamable-http, auto-reconnect, HMR hot-swap.

中文文档见 README.zh.md。

Feedback

Installs are visible in the download counts; whether this helps is not. If you use it, one line about the actual task is worth more than a star — particularly if it did not work, which is the case that never gets reported:

• what you were trying to do
• whether it did it
• what was missing or wrong

Tell me in an issue — or if something is already broken, just open a normal bug report.

Requirements

This package is a configuration layer, not a plugin of its own. Its cordis.patch.yml inserts entries that point at @deepseek-ai/dsh-mcp-client, which the host provides.

• @deepseek-ai/dsh-mcp-client must be installed in the profile you are adding this to, at the version matching your DSH line.
• It is declared as a permissive optional peer (>=0.1.0-rc.6) rather than a dependency. Pinning it previously forced an old copy into the tree whose own peers (dsh-tools@^0.0.1-rc.1) conflict with current DSH releases, which made installation fail on version resolution. Reported as issue #2.

If installation fails, check that the client version in your profile matches your DSH version:

npm view @deepseek-ai/dsh-mcp-client versions --json | tail -20

Interactive installer

npx dsh-mcp-bridge init          # pick servers interactively
npx dsh-mcp-bridge list          # catalog + verification status
npx dsh-mcp-bridge validate      # list the MCP entries already in a profile

init writes real insert: entries into the profile's user patch layer ($DSH_HOME/profiles/<name>/cordis.patch.yml), so your selection survives plugin upgrades and coexists with your own patches. It warns about servers that need environment variables or a placeholder path to edit.

Why not just configure the MCP servers yourself?

Because the fiddly parts are not the YAML — they are everything around it.

• The user patch layer overrides existing entries; naming a new id there fails with patch: entry "x" not found. New servers need insert:.
• Config nested one level too shallow parses to config: null, and the server silently never starts.
• A server that connects but exposes no tools looks exactly like a working one until you ask the model.

This bundle ships working shapes, an installer that writes them correctly (init), inspectors (list, validate) and a verifier that actually connects.

Quick start

Prereqs: dsh and pnpm on PATH (dsh plugin forwards to pnpm; install with npm i -g pnpm).

dsh plugin --profile web add dsh-mcp-bridge
# local checkout:  dsh plugin --profile web add ./dsh-mcp-bridge
dsh web        # restart the profile

The demo server (MCP official everything) is enabled by default — no API key, pure local npx. After restart, ask your model to "call the everything server's echo tool with hello" and it should use mcp__everything__echo.

First run downloads the server packages via npx; subsequent runs are cached.

Curated catalog

To enable a commented preset, uncomment its block in the profile's cordis.patch.yml (hot-reloaded via HMR) or edit cordis.patch.yml in this package.

Verify the catalog yourself

npm install          # brings @deepseek-ai/dsh-mcp-client → the MCP SDK
npm run verify       # or: node scripts/verify-servers.mjs

Prints PASS / SKIP / FAIL per server; exits non-zero on any failure. VERIFY_TIMEOUT_MS=15000 tunes the per-server timeout. Single-server troubleshooting: node scripts/probe-server.mjs npx -y your-mcp-server.

Adding your own MCP server

Each server is one @deepseek-ai/dsh-mcp-client entry. Either add it to the profile's user patch layer (recommended, HMR applies it without restart):

# $DSH_HOME/profiles/<name>/cordis.patch.yml
- id: mcp-myserver
  name: '@deepseek-ai/dsh-mcp-client'
  config:
    serverName: myserver          # namespace, unique per process ([A-Za-z0-9_-]{1,32})
    transport: stdio              # or streamable-http
    command: npx
    args: ['-y', 'your-mcp-server']
    env:
      YOUR_TOKEN: !!js process.env.YOUR_TOKEN

…or drop a definition into servers/ (so verify covers it) and add the matching entry to cordis.patch.yml here.

Config fields (from dsh-mcp-client)

Linking up with Reasonix / CodeWhale

All three are agent harnesses — MCP is the shared language. Any server you run for Reasonix or CodeWhale can be added here, and a local streamable-http server you own can serve DSH, Reasonix and CodeWhale from one process. See servers/remote-http.json.

Troubleshooting (Windows)

• Headless verification hangs (dsh --profile <name> "task"): the profile needs @deepseek-ai/dsh-headless in dsh.profile.bundles (add it manually; dsh plugin add @deepseek-ai/dsh-headless fails with 404 on its unpublished dependency). Without it the tree activates but no agent consumes the task.
• npx is fine on Windows: the MCP SDK uses cross-spawn, which resolves .cmd shims — no npx.exe needed.
• Server connects but no tools: check the profile logs; failOnStartupError: false means the entry activates without tools on failure.

Releasing (npm)

1. npm version patch (or bump package.json manually), commit, tag vX.Y.Z.
2. git push origin main --tags.
3. GitHub Actions (publish.yml) publishes to npm — requires npm trusted publisher (OIDC) linked to the repo. Setup: npm → Access Tokens → Generate new token → Publish with GitHub Actions.

Give the repo the GitHub topic dsh-plugin so it shows up in the community lists (awesome-dsh-plugin, WhaleHub).

License

MIT — see LICENSE.

A server that is not in the list

The catalog is a starting point, not a ceiling. add installs any npm-published MCP server into a profile and then probes it, so the result is "it works" or "here is what broke":

npx dsh-mcp-bridge add @modelcontextprotocol/server-memory
npx dsh-mcp-bridge add some-mcp-server --name some --env SOME_API_KEY

Wrote memory (@modelcontextprotocol/server-memory) to ~/.dsh/profiles/web/cordis.patch.yml

Checking that it actually starts...
  OK — 9 tool(s) listed

If the probe fails, the entry stays written so you can fix it in place, and the message says where:

  FAILED at connect: MCP error -32000: Connection closed
  the entry is still written so you can fix it in place:
    ~/.dsh/profiles/web/cordis.patch.yml

Options: --profile <name> (defaults to the first profile), --name <serverName> (defaults to a name derived from the package), --args a,b (extra arguments), --env KEY1,KEY2 (environment variables passed through from the environment), --timeout <seconds>.

Removing a server

npx dsh-mcp-bridge remove memory --profile web

Removes one - insert: entry from the profile's patch layer, leaving every other entry and the header comment alone. --dry-run shows what would be removed without writing; an unknown name exits 2 and lists the entries that are present. Restart the profile for it to take effect.

When a server does not start

Installing is half the job. When a server never appears in your tool list, doctor starts each one, completes the MCP handshake and lists its tools, so you can see where it broke:

npx dsh-mcp-bridge doctor

Diagnosing 7 curated server(s), 60s each…

  ✅ everything     16 tools
  ⏸  filesystem     needs configuration first — MCP error -32000: Connection closed
       → fill in its settings before diagnosing: npx -y @modelcontextprotocol/server-filesystem C:/path/to/allowed/root
  ⏸  github         needs GITHUB_TOKEN
  ✅ memory         9 tools
  ✅ playwright     25 tools
  ⏸  remote         needs MCP_TOKEN
  ✅ sequential-thinking 1 tools

4 ok, 3 skipped, 0 failed

Failed stages are reported separately because the advice differs:

Servers that are simply not configured yet are reported as skipped, not failed — a placeholder path is not a bug.

Other commands: list (catalog), init (install), validate (what is in a profile).

Related

Part of the dsh-toolkit family — small, independently useful pieces for DeepSeek Harness:

• dsh-mcp-bridge — install six curated MCP servers, verified in CI
• dsh-win-toolkit — clipboard, notifications, hosts, port checks on Windows
• dsh-netassist — network and proxy diagnosis with a concrete next step
• dsh-driftwatch — behaviour-drift reports between two session logs
• dsh-ledger — what the agent did to your files, provably unaltered
• dsh-release-evidence — one verifiable artifact per release
• mcp-netassist — the same network checks as an MCP server, any client