Meeba Brain

Official5 toolsLive

by meemoprasad

Repository knowledge graph MCP server for codebase understanding and debugging.

meeba-brain (MCP Server)

io.github.meemoprasad/meeba-brain provides a ground-truth code graph for a codebase, capturing exact callers, callees, symbols, and dependencies. This MCP server exposes these relationships through its available tools (5 total), enabling retrieval of code-structure data derived from the underlying repository.

🛠️ Key Features

Ground-truth code graph generation
Exact callers and callees mapping
Symbols extraction
Dependencies identification
5 tools exposed via the server

🚀 Use Cases

Inspect call relationships within a codebase
Explore symbol usage and linkage
Understand inter-module or package dependencies

⚡ Developer Benefits

Supports accurate code-relationship queries using exact callers/callees
Provides structured dependency and symbol context for development workflows

⚠️ Limitations

Details beyond the code graph scope (e.g., specific query formats or tool capabilities) are not provided in the available metadata.

Topics

call-graphclaude-codeclaude-code-plugincode-graphcode-intelligencecode-intelligence-mcpcode-understandingcodebase-contextcursorcursor-plugindebuggingdebugging-toolknowledge-graphmcpmcp-server

Captured live from the server via tools/list.

search_code

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.

Parameters2

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

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Natural-language or keyword description of what you're looking for."
    },
    "top_k": {
      "default": 8,
      "type": "integer",
      "description": "Max number of results to return (default 8, max 20)."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

get_symbol_definition

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.

Parameters1

name

string

required

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.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "The bare symbol name (e.g. \"get_upstream_impact\"), or\n\"ClassName.method_name\" for a specific method when the bare\nname is ambiguous across multiple classes."
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false
}

get_callers

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.

Parameters1

function_name

string

required

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

Raw schema

{
  "type": "object",
  "properties": {
    "function_name": {
      "type": "string",
      "description": "The bare function/method name (e.g. \"save_user\").\nIf multiple unrelated symbols share this name, results are\ngrouped by which definition they call."
    }
  },
  "required": [
    "function_name"
  ],
  "additionalProperties": false
}

get_callees

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.

Parameters1

function_name

string

required

The bare function/method name (e.g. "sync_repository").

Raw schema

{
  "type": "object",
  "properties": {
    "function_name": {
      "type": "string",
      "description": "The bare function/method name (e.g. \"sync_repository\")."
    }
  },
  "required": [
    "function_name"
  ],
  "additionalProperties": false
}

get_dependencies

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.

Parameters1

file_path

string

required

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).

Raw schema

{
  "type": "object",
  "properties": {
    "file_path": {
      "type": "string",
      "description": "Repo-relative path (e.g. \"utils/knowledge_graph/graph_builder.py\").\nMatches by exact path first, then by suffix if no exact match\n(so \"graph_builder.py\" alone will still resolve if unambiguous)."
    }
  },
  "required": [
    "file_path"
  ],
  "additionalProperties": false
}

README.md5 KBView on GitHub

Meeba Brain MCP

Repository Knowledge Graph for Cursor

Give your AI coding assistant a structural understanding of your codebase.

Meeba Brain MCP connects Cursor to Meeba Brain's repository knowledge graph, helping it understand how functions, files, services, and dependencies are connected.

Instead of relying only on text search, Cursor can use Meeba Brain's structural context to investigate unfamiliar code, trace relationships, and reason about changes with better grounding.

Why Meeba Brain?

Text search helps you find where a name or phrase appears.

A knowledge graph helps you understand how the code is connected.

For example, instead of only finding refundOrder, you can investigate:

Which services call this function?
What does this function call?
How does this API connect to the underlying implementation?
Which parts of the codebase may be affected by this change?

The difference is not simply finding more text. It is understanding the relationships between the code.

How does this help with the correct fix?

When debugging, the file showing the error is not always the file causing the problem.

A bug may involve several connected components:

API route → service → worker → dependency

Without understanding those relationships, an AI assistant may suggest a plausible fix that changes the wrong layer or misses an affected caller.

Meeba Brain provides Cursor with repository-grounded structural context so Cursor can investigate the relevant relationships before proposing a change.

This helps Cursor identify the relevant code, understand potential impact, and propose better-informed fixes.

Meeba Brain does not guarantee that every fix is correct. Its purpose is to give Cursor better evidence and structural context for reaching the right fix.

What the MCP provides

Meeba Brain MCP provides access to repository knowledge graph capabilities, including:

Symbol relationships
Callers and callees
Dependencies
Repository structure
Structural context for code investigation

How to use Meeba Brain MCP

Meeba Brain MCP requires a connected, indexed repository.

The repository is connected and indexed on Meeba Brain, not inside Cursor.

1. Create your account

Go to:

https://meeba.ai/brain

2. Connect your repository

After signing in, connect the repository you want to investigate on Meeba Brain.

3. Wait for indexing to finish

Meeba Brain needs to build the repository's structural knowledge graph.

Wait until indexing is complete before connecting the MCP to Cursor.

4. Enable MCP and get your key

Open the MCP connection page:

https://meeba.ai/brain/connect

Enable MCP and copy the key provided by Meeba Brain.

Keep this key private.

5. Add Meeba Brain MCP to Cursor

In Cursor:

Open Settings.
Go to Tools & Integrations → MCP.
Click Add Custom MCP or Add New MCP Server.
Select the HTTP / remote MCP connection option.
Enter the Meeba Brain MCP server URL shown on the connection page.
Add the authentication header using your Meeba Brain MCP key.
Save the configuration.

Use the exact server URL and authentication header shown in Meeba Brain.

6. Enable the server in Cursor

After saving the configuration, open the MCP settings and make sure Meeba Brain is enabled.

7. Ask Cursor a question about your codebase

Open your repository in Cursor and ask a question such as:

"Which services call refundOrder()?"

"Explain how this feature flows through the codebase."

"What could be affected if I change this API?"

"Trace the code flow from this route to the implementation."

"Why is this function being called?"

Start with one real function, dependency, or bug you want to understand.

Important distinction

Meeba Brain MCP is not a replacement for Cursor.

It is a repository knowledge graph integration that gives Cursor additional structural context.

Cursor remains responsible for the coding conversation, reasoning, and code changes.

Meeba Brain provides the repository intelligence that helps make that reasoning more grounded.

Best for

Developers working in unfamiliar repositories
Debugging code that spans multiple files or services
Understanding dependencies before making changes
Investigating the impact of a refactor
Developers who want more structural grounding from their AI coding assistant

Get started

Learn about Meeba Brain:

https://meeba.ai/brain

Connect your repository and enable MCP:

https://meeba.ai/brain/connect

Understand the relationships. Investigate the evidence. Make better-informed changes.

Install

Tools (5)

search_codeget_symbol_definitionget_callersget_calleesget_dependencies

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://meeba-context-mcp-469248886325.us-central1.run.app/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "meeba-brain": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://meeba-context-mcp-469248886325.us-central1.run.app/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

meeba-brain (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

search_code

get_symbol_definition

get_callers

get_callees

get_dependencies

Meeba Brain MCP

Repository Knowledge Graph for Cursor

Why Meeba Brain?

How does this help with the correct fix?

What the MCP provides

How to use Meeba Brain MCP

1. Create your account

2. Connect your repository

3. Wait for indexing to finish

4. Enable MCP and get your key

5. Add Meeba Brain MCP to Cursor

6. Enable the server in Cursor

7. Ask Cursor a question about your codebase

Important distinction

Best for

Get started

Install

Remote endpoint

Related servers