mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-29 21:57:14 +00:00
Junyan Chin
e9dd584792
* feat(api): support global API key from config.yaml (api.global_api_key) Accept a config-defined global API key anywhere a web-UI key is accepted (X-API-Key / Bearer), with no login session and no DB record. Useful for automated deployments and AI agents (HTTP API + MCP). Defaults to empty (disabled); does not require the lbk_ prefix. - templates/config.yaml: add api.global_api_key with security notes - service/apikey.py: verify_api_key checks global key first (constant-time) - docs/API_KEY_AUTH.md: document the global key + security guidance - tests: cover global-key match, prefix-free, fallback-to-db, disabled * feat(mcp): expose LangBot management as an MCP server at /mcp Add an MCP (Model Context Protocol) server so external AI agents can manage a LangBot instance. Reuses the same API-key auth as the HTTP API (including the config.yaml global API key). - pkg/api/mcp/server.py: FastMCP server wrapping the service layer; 21 curated tools across system/bots/pipelines/models/knowledge/mcp-servers/skills - pkg/api/mcp/mount.py: ASGI dispatcher fronting Quart; authenticates /mcp requests with an API key, runs the streamable-HTTP session manager lifespan - controller/main.py: serve the wrapped ASGI app via hypercorn (was run_task) - web: new 'MCP' tab in the API integration dialog showing endpoint, auth, and client config; i18n for 8 locales - tests/manual/mcp_smoke.py: e2e check (401 unauth, list tools, call tools) Tool surface is intentionally curated (not all ~25 route groups) to keep the agent surface small, safe, and maintainable. Extend deliberately. * feat(skills): add in-repo skills/ as the single source of truth Migrate the agent skills + QA/e2e test harness from the (now archived) langbot-app/langbot-skills repo into LangBot/skills/, and add four new skills. Migrated: - langbot-plugin-dev, langbot-testing (e2e), langbot-env-setup, langbot-skills-maintenance, langbot-eba-adapter-dev - the bin/lbs CLI (src/, test/, scripts/, schemas/, qa-agent-docs/) New: - langbot-dev core backend + web development - langbot-deploy Docker/K8s deployment + config.yaml + global API key - langbot-mcp-ops operating the LangBot MCP server (/mcp) - langbot-space-ops operating the Space marketplace MCP server - src/cli.ts repoRoot(): recognize the skills assets root (skills.index.json + bin/lbs) so the CLI works when nested inside the LangBot repo - README.md: unified skill catalog; skills.index.json regenerated Parity with source verified: bin/lbs validate + node test suite match the source repo (only the uncommitted .lbpkg build-artifact fixture differs). * docs(agents): document agent-facing surfaces + API/MCP/skills sync rule * docs(readme): add 'Built for AI Agents' section across all locales Highlight MCP server, in-repo skills (single source of truth), AGENTS.md sync rule, and llms.txt. Cross-link LangBot Space MCP marketplace. * style(mcp): fix ruff format + prettier lint in MCP server and API panel * style(web): prettier format MCP i18n locale entries * docs(skills): note MCP instance control in dev/testing skills All development-guidance skills now point to the LangBot instance MCP server (/mcp) and the Space marketplace MCP server, reusing API keys.
37 lines
2.4 KiB
YAML
37 lines
2.4 KiB
YAML
id: mcp-stdio-args-not-applied
|
|
title: "MCP Stdio test runs only the command without arguments"
|
|
date: 2026-05-17
|
|
symptoms:
|
|
- "The MCP server Test button fails even though the same command works in a terminal."
|
|
- "Backend logs show uv help text or another bare command output instead of starting the MCP server."
|
|
- "Backend logs show uv: not found after the fixture path is accepted by Box."
|
|
- "Backend logs show host_path is outside allowed_mount_roots before the stdio process starts."
|
|
- "The task exception is Connection failed, please check URL or Connection closed."
|
|
- "Backend startup logs say qa_mcp_echo_server.py cannot be opened from the LangBot repo root."
|
|
patterns:
|
|
- "An extremely fast Python package manager."
|
|
- "Usage: uv [OPTIONS] <COMMAND>"
|
|
- "/bin/sh: 1: uv: not found"
|
|
- "host_path is outside allowed_mount_roots"
|
|
- "McpError: Connection closed"
|
|
- "mcp-test-_"
|
|
- "can't open file '.../LangBot/qa_mcp_echo_server.py'"
|
|
likely_causes:
|
|
- "Box refuses to mount the bundled fixture directory because it is not listed in box.local.allowed_mount_roots."
|
|
- "The saved MCP server command uses uv, but uv is not available inside the Box runtime PATH."
|
|
- "The WebUI did not pass the current stdio args to the test request."
|
|
- "The MCP form exposed a stale imperative test handler from an old render."
|
|
- "The user entered the whole command line into the command field instead of splitting command and args."
|
|
- "An old qa-local-stdio database record still points at a temporary LangBot root script instead of the bundled skills fixture."
|
|
fix_steps:
|
|
- "Confirm the fixture directory is listed in box.local.allowed_mount_roots for the local LangBot data config."
|
|
- "Confirm command is only the executable, normally python for this fixture."
|
|
- "Confirm args are separate entries; for this fixture use the server script path as the single arg."
|
|
- "Confirm the fixture script is the current dependency-free qa_mcp_echo_server.py."
|
|
- "For qa-local-stdio, set the server script path to the absolute skills fixture path: skills/langbot-testing/fixtures/mcp/qa_mcp_echo_server.py."
|
|
- "If the UI still sends empty args, fix the MCP form test handler so it reads the latest state."
|
|
- "Retest with the bundled qa_mcp_echo_server.py fixture."
|
|
verification: "The MCP test task completes without exception, the saved server shows connected, and /api/v1/tools contains qa_mcp_echo."
|
|
related_cases:
|
|
- mcp-stdio-tool-call
|