trelix-mcp

MCP server for trelix v3.1.5 — semantic code search with streaming /ask endpoint, watch bridge notifications, and REST API integration for Claude Code, Cursor, Windsurf, and Continue.dev.

⚠️ Breaking Change in v2.4.0

search_code now returns a pagination envelope instead of a bare list:

# v2.3.x (old)
results = search_code(query="auth", repo_path="/repo")
for r in results:  # results was list[dict]
    print(r["symbol"])

# v2.4.0 (new)
response = search_code(query="auth", repo_path="/repo")
for r in response["results"]:  # now dict with pagination
    print(r["symbol"])
# Paginate: pass response["next_cursor"] as cursor= for next page

Install

pip install trelix-mcp

Unpinned on purpose. trelix-mcp carries the core version stamp and is published only by a core v* tag, so the newest trelix-mcp is always the one built alongside the newest trelix. To pin in your own requirements.txt, pin all four distributions to the same version — see the FAQ.

To use Bedrock embeddings or synthesis (no extra API key beyond AWS credentials):

pip install trelix-mcp "trelix[bedrock]"

Other optional LLM provider extras:

pip install trelix-mcp "trelix[anthropic]"   # Anthropic Claude direct
pip install trelix-mcp "trelix[vertex]"      # Google Vertex AI / Gemini
pip install trelix-mcp "trelix[litellm]"     # 100+ providers via LiteLLM
pip install trelix-mcp "trelix[llm-all]"     # all LLM providers

Usage

Claude Code

claude mcp add trelix -- trelix-mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "trelix": {
      "command": "trelix-mcp",
      "args": []
    }
  }
}

Continue.dev (.continue/config.json)

{
  "mcpServers": [
    {
      "name": "trelix",
      "command": "trelix-mcp",
      "args": []
    }
  ]
}

Configuration

Set environment variables before starting the MCP server. All variables are optional — defaults work out of the box with the local embedding provider and openai chat provider.

Embedding provider

# Local sentence-transformers — no API key (default)
TRELIX_EMBEDDER_PROVIDER=local

# Local BGE Code — EXPERIMENTAL: pooling unverified, no quality claim, no API key
TRELIX_EMBEDDER_PROVIDER=bge-code

# Local Nomic Code — competitive code embeddings, no API key
TRELIX_EMBEDDER_PROVIDER=nomic-code

# Azure OpenAI embeddings
TRELIX_EMBEDDER_PROVIDER=azure
AZURE_API_KEY=...
AZURE_ENDPOINT=https://<resource>.openai.azure.com/

# Voyage AI — best API-based code embeddings (CoIR 56.26)
TRELIX_EMBEDDER_PROVIDER=voyage
VOYAGE_API_KEY=...

# AWS Bedrock Cohere — strong code retrieval, no extra key beyond AWS creds
TRELIX_EMBEDDER_PROVIDER=bedrock-cohere
AWS_ACCESS_KEY_ID=...
AWS_SECRET_ACCESS_KEY=...
AWS_REGION=us-east-1

# AWS Bedrock Titan v2 — configurable 256/512/1024 dims
TRELIX_EMBEDDER_PROVIDER=bedrock-titan
AWS_ACCESS_KEY_ID=...
AWS_SECRET_ACCESS_KEY=...
AWS_REGION=us-east-1

Chat / synthesis provider (used by index_codebase contextual chunking and synthesis)

# OpenAI (default)
TRELIX_LLM_PROVIDER=openai
OPENAI_API_KEY=sk-...

# Azure GPT-4o
TRELIX_LLM_PROVIDER=azure
AZURE_API_KEY=...
AZURE_ENDPOINT=https://<resource>.openai.azure.com/

# AWS Bedrock — Claude Sonnet 4.6 default with auto-fallback to Haiku
TRELIX_LLM_PROVIDER=bedrock
AWS_ACCESS_KEY_ID=...
AWS_SECRET_ACCESS_KEY=...
AWS_REGION=us-east-1
# Optional overrides:
TRELIX_LLM_BEDROCK_PRIMARY_MODEL=us.anthropic.claude-sonnet-4-6
TRELIX_LLM_BEDROCK_FALLBACK_MODEL=us.anthropic.claude-haiku-4-5-20251001-v1:0

# Anthropic direct
TRELIX_LLM_PROVIDER=anthropic
ANTHROPIC_API_KEY=sk-ant-...

# Google Vertex AI / Gemini
TRELIX_LLM_PROVIDER=vertex
GOOGLE_CLOUD_PROJECT=my-project
GOOGLE_CLOUD_LOCATION=us-central1

# LiteLLM — 100+ providers
TRELIX_LLM_PROVIDER=litellm
TRELIX_LLM_MODEL=bedrock/claude-3-5-sonnet

Resource subscription limits

# Max concurrent resource subscriptions across all clients — caps unbounded
# growth from a client that subscribes repeatedly without ever unsubscribing
TRELIX_MCP_MAX_SUBSCRIBERS=1000

# Auto-evict a subscription after this many seconds of inactivity
TRELIX_MCP_SUBSCRIPTION_TTL_SECONDS=3600

Tools

Multi-Repo Federation Tools (v2.8.0)

Persistent Agent Session Tools (v2.8.0)

Resource Subscriptions (v2.5.0)

trelix-mcp supports live index change notifications. When trelix watch detects a file change, connected MCP clients receive a notifications/resources/updated push — then call resources/read to fetch the updated index. Subscribe with the subscribe_resource tool.

# Subscribe to a repo manifest
subscribe_resource(
    uri="trelix://repo//path/to/repo/manifest",
    subscription_id="my-sub-001"
)
# → client receives notifications/resources/updated when trelix watch fires
# → call resources/read on the URI to get the refreshed index

# Cancel the subscription
unsubscribe_resource(subscription_id="my-sub-001")

The resources.subscribe capability is advertised in server capabilities. URIs follow the scheme trelix://repo/{repo_path}/manifest. The notify_file_changed() hook (wired into FileWatcher._do_reindex since v2.7.0) fires per-URI notifications with the subscriptionId in params._meta.

Subscriptions are capped and TTL'd by default — see Resource subscription limits (TRELIX_MCP_MAX_SUBSCRIBERS, default 1000; TRELIX_MCP_SUBSCRIPTION_TTL_SECONDS, default 3600). Subscriptions older than the TTL are swept on the next registry access. If the registry is at capacity, subscribe_resource does not raise — it returns {"subscribed": false, "uri": ..., "subscription_id": ..., "error": "..."} so callers can handle rejection gracefully.

Pagination

search_code supports cursor-based pagination for large codebases:

# Fetch page 1
page1 = search_code(query="authentication", repo_path="/repo", k=10)
print(page1["total_available"])  # total results
print(page1["results"])          # this page's results

# Fetch page 2 if more results exist
if page1["next_cursor"] is not None:
    page2 = search_code(query="authentication", repo_path="/repo", k=10, cursor=page1["next_cursor"])

Knowledge Graph Tools

Two tools expose the knowledge graph layer to AI agents:

build_knowledge_graph

Builds a Code Property Graph over an indexed repo. Returns node/edge counts, community count, and a summary of top architectural clusters.

build_knowledge_graph(repo_path="/path/to/repo")
→ {node_count: 4599, edge_count: 4945, community_count: 2409, community_summary: [...]}

Use this before graph_search_mcp for best results — or let graph_search_mcp call it automatically.

graph_search_mcp

Hybrid search: first retrieves semantic seeds, then expands via BFS over call/import/type edges.

graph_search_mcp(query="how does auth relate to the user model?", repo_path="/path/to/repo", k=10)
→ [{file, symbol, kind, score, source, body}, ...]

When to use graph_search_mcp instead of search_code:

• "What does X depend on?"
• "What would break if I change Y?"
• "How does module A connect to module B?"
• Architecture understanding queries where structural relationships matter

Install the knowledge graph extra for full functionality:

pip install trelix-mcp 'trelix[knowledge-graph]'

Watch Bridge (v2.7.0)

The trelix watch command now fires MCP notifications after every file re-index, allowing real-time codebase awareness across all subscribed clients:

# Terminal 1: Start trelix-mcp
trelix-mcp

# Terminal 2: Enable file watching
trelix watch /path/to/repo

Clients subscribe to a repository's manifest URI via subscribe_resource, which takes two required strings. There is no glob support:

subscribe_resource(uri="trelix://repo//path/to/repo/manifest", subscription_id="my-sub-001")

After each re-index, subscribed clients receive notifications/resources/updated carrying only {"uri": ..., "_meta": {"subscriptionId": ...}} — no file paths and no stats. Call resources/read on that URI to see what changed.