Meeba Brain

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Repository knowledge graph MCP server for codebase understanding and debugging.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Meeba Brain": {
      "url": "https://meeba-context-mcp-469248886325.us-central1.run.app/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• search_code read-only

  Hybrid semantic + keyword search over the connected repository's actual indexed content. Use this for open-ended questions ("where is rate limiting implemented?", "how are uploads validated?") where you don't already know an exact symbol or file name -- for those, use get_symbol_definition or get_dependencies instead, they're more precise.

  Parameters:

  • query (required) — string — Natural-language or keyword description of what you're looking for.
  • top_k — integer — Max number of results to return (default 8, max 20).

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_symbol_definition read-only

  Finds where a function, class, or method is actually defined in this repo -- exact file, line range, and signature-relevant metadata (async, decorators, docstring if present). Use this before assuming a symbol's location/signature from memory or from a similarly-named symbol in a different file.

  Parameters:

  • name (required) — string — The bare symbol name (e.g. "get_upstream_impact"), or "ClassName.method_name" for a specific method when the bare name is ambiguous across multiple classes.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_callers read-only

  Every place in this repo that calls the given function or method -- a COMPLETE list from the parsed call graph, not a best-effort guess. Use this before renaming/changing a function's signature, or when you need to understand a function's blast radius before modifying it.

  Parameters:

  • function_name (required) — string — The bare function/method name (e.g. "save_user"). If multiple unrelated symbols share this name, results are grouped by which definition they call.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_callees read-only

  Every function/method the given function calls -- what it depends on to do its job. Use this to understand a function's behavior by seeing what it delegates to, before assuming what it does from its name alone.

  Parameters:

  • function_name (required) — string — The bare function/method name (e.g. "sync_repository").

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_dependencies read-only

  What a specific file imports/depends on. Use this to understand a file's place in the codebase before assuming what's available to it, or before moving/refactoring it.

  Parameters:

  • file_path (required) — string — Repo-relative path (e.g. "utils/knowledge_graph/graph_builder.py"). Matches by exact path first, then by suffix if no exact match (so "graph_builder.py" alone will still resolve if unambiguous).

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.