Commit Graph

6 Commits

Author SHA1 Message Date
teknium1
60effcfc44 fix(mcp): parallel discovery, user-visible logging, config validation
- Discovery is now parallel (asyncio.gather) instead of sequential,
  fixing the 60s shared timeout issue with multiple servers
- Startup messages use print() so users see connection status even
  with default log levels (the 'tools' logger is set to ERROR)
- Summary line shows total tools and failed servers count
- Validate conflicting config: warn if both 'url' and 'command' are
  present (HTTP takes precedence)
- Update TODO.md: mark MCP as implemented, list remaining work
- Add test for conflicting config detection (51 tests total)

All 1163 tests pass.
2026-03-02 19:02:28 -08:00
teknium1
64ff8f065b feat(mcp): add HTTP transport, reconnection, security hardening
Upgrades the MCP client implementation from PR #291 with:

- HTTP/Streamable HTTP transport: support 'url' key in config for remote
  MCP servers (Notion, Slack, Sentry, Supabase, etc.)
- Automatic reconnection with exponential backoff (1s-60s, 5 retries)
  when a server connection drops unexpectedly
- Environment variable filtering: only pass safe vars (PATH, HOME, etc.)
  plus user-specified env to stdio subprocesses (prevents secret leaks)
- Credential stripping: sanitize error messages before returning to the
  LLM (strips GitHub PATs, OpenAI keys, Bearer tokens, etc.)
- Configurable per-server timeouts: 'timeout' and 'connect_timeout' keys
- Fix shutdown race condition in servers_snapshot variable scoping

Test coverage: 50 tests (up from 30), including new tests for env
filtering, credential sanitization, HTTP config detection, reconnection
logic, and configurable timeouts.

All 1162 tests pass (1162 passed, 3 skipped, 0 failed).
2026-03-02 18:40:03 -08:00
0xbyt4
11a2ecb936 fix: resolve thread safety issues and shutdown deadlock in MCP client
- Add threading.Lock protecting all shared state (_servers, _mcp_loop, _mcp_thread)
- Fix deadlock in shutdown_mcp_servers: _stop_mcp_loop was called inside
  a _lock block but also acquires _lock (non-reentrant)
- Fix race condition in _ensure_mcp_loop with concurrent callers
- Change idempotency to per-server (retry failed servers, skip connected)
- Dynamic toolset injection via startswith("hermes-") instead of hardcoded list
- Parallel shutdown via asyncio.gather instead of sequential loop
- Add tests for partial failure retry, parallel shutdown, dynamic injection
2026-03-02 22:08:32 +03:00
0xbyt4
593c549bc4 fix: make discover_mcp_tools idempotent to prevent duplicate connections
When discover_mcp_tools() is called multiple times (e.g. direct call
then model_tools import), return existing tool names instead of opening
new connections that would orphan the previous ones.
2026-03-02 21:34:21 +03:00
0xbyt4
aa2ecaef29 fix: resolve orphan subprocess leak on MCP server shutdown
Refactor MCP connections from AsyncExitStack to task-per-server
architecture. Each server now runs as a long-lived asyncio Task
with `async with stdio_client(...)`, ensuring anyio cancel-scope
cleanup happens in the same Task that opened the connection.
2026-03-02 21:22:00 +03:00
0xbyt4
3c252ae44b feat: add MCP (Model Context Protocol) client support
Connect to external MCP servers via stdio transport, discover their tools
at startup, and register them into the hermes-agent tool registry.

- New tools/mcp_tool.py: config loading, server connection via background
  event loop, tool handler factories, discovery, and graceful shutdown
- model_tools.py: trigger MCP discovery after built-in tool imports
- cli.py: call shutdown_mcp_servers in _run_cleanup
- pyproject.toml: add mcp>=1.2.0 as optional dependency
- 27 unit tests covering config, schema conversion, handlers, registration,
  SDK interaction, toolset injection, graceful fallback, and shutdown

Config format (in ~/.hermes/config.yaml):
  mcp_servers:
    filesystem:
      command: "npx"
      args: ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
2026-03-02 21:03:14 +03:00