Skip to main content
Glama
zaebee

codegraph-brain

by zaebee
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to codegraph-brain

  • CodeGraph

    colbymchenry
    A
    license
    Not graded
    quality
    A
    maintenance
    Supercharges AI coding agents with a pre-indexed semantic code graph, enabling instant symbol relationships, impact analysis, and context retrieval across 20+ languages.
    140,534 npm
    73,402
    MIT

Related Servers

  • codegraph

    mooyee0929
    A
    license
    B
    quality
    C
    maintenance
    Indexes a Python/JS/TS repository into a local SQLite knowledge graph so agents can trace callers, callees, imports, subclasses and covering tests, measure impact radius, rank diff risk, and summarize architecture without grepping files. Exposes these queries as MCP tools alongside an equivalent CLI, with no daemon, embeddings, or network access.
    10
    MIT

  • Idencify

    jospnunes
    A
    license
    B
    quality
    C
    maintenance
    Whole-repo code graph for AI agents: impact analysis, dead code, cycles, semantic code search — 14 tools via hosted MCP endpoint.
    15
    MIT

  • mcp-code-indexer-react-ts

    Nishant-Chaudhary5338
    A
    license
    A
    quality
    B
    maintenance
    Indexes any TypeScript / React / Next.js repo into a queryable code graph and exposes 13 MCP tools — who-renders, who-calls, find-references, blast-radius, find-cycles, dead-code orphans, and local semantic search — so agents query structure instead of reading whole files. Built on ts-morph, so edges are resolved, not grepped.
    14
    2
    MIT
  • mcp-reposkein by reposkein

    mcp-reposkeinofficial

    reposkein
    A
    license
    A
    quality
    A
    maintenance
    Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP. Python, TS/JS, Rust, Go, Java, C#.
    8
    12
    Apache 2.0
  • loctree-mcp by Loctree

    loctree-mcpofficial

    Loctree
    F
    license
    Not graded
    quality
    A
    maintenance
    Structural code intelligence for AI agents. Scan once, query everything — dead exports, circular imports, dependency graphs, and more. CLI + MCP server.
    6 npm
    9
    -

  • CodeGraph

    codegraph-ai
    A
    license
    Not graded
    quality
    Not graded
    maintenance
    CodeGraph — Open-source code intelligence MCP server. Builds a semantic graph of your codebase (functions, classes, imports, call chains) and exposes it through 31 tools. Callers, callees, impact analysis, complexity metrics, unused code detection, AI context assembly, persistent memory, cross-project search. 15 languages via tree-sitter. Single Rust binary, local-first.
    301 npm
    -
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A4.4/5.0

Scored across 15 tools

Disambiguation4/5

The core navigation tools are cleanly split: cgis_trace_flow (downstream) vs cgis_analyze_impact (upstream) vs cgis_get_structure (containment) vs cgis_context (single-node brief), and descriptions explicitly cross-reference each other to steer selection. The only soft spot is a cluster of whole-graph analytics tools (cgis_metrics, cgis_fractal, cgis_drift, cgis_suggest_packages, cgis_audit_reachability) whose boundaries are clear in prose but overlap conceptually as 'architectural reports'.

Naming Consistency4/5

Every tool shares a uniform cgis_ prefix and snake_case, so the family is immediately recognizable and readable. It is not a strict verb_noun scheme, though: verbs like cgis_ingest/cgis_validate/cgis_find_symbol mix with bare nouns like cgis_fractal, cgis_drift, cgis_metrics, cgis_overview, cgis_context — consistent convention, slightly loose semantics.

Tool Count5/5

15 tools sits at the upper edge of the ideal band but each one targets a distinct analysis or lifecycle step (ingest, overview, find, trace, impact, structure, context, metrics, fractal, drift, packages, orphans, audit, ontology, validate). No tool feels redundant or filler for a code-graph analysis server of this scope.

Completeness4/5

The surface covers the full lifecycle: ingest/refresh, discovery (overview, find_symbol), traversal (trace_flow, impact, structure, context), analytics (metrics, fractal, drift, packages, orphans), and integrity (validate, audit_reachability, init_ontology). Minor gaps exist — no explicit tool to drop/replace or diff a graph DB, and no direct edge/symbol mutation — but these are reasonable omissions rather than dead ends.

Maintenance

ActivityActive
ResponsivenessResponsive

Resources