Skip to main content
Glama
yesheng-oss

Context-MCP

by yesheng-oss

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
codegraph_buildA

Scan a project directory and build the knowledge graph from code files. Uses tree-sitter AST (with regex fallback) for all code files. Fast, local, no API key needed. Run once per project; rebuild whenever code changes.

codegraph_queryA

Ask a structural question about the codebase OR look up a specific node by name — or both in one call. Pass question for natural-language traversal: what calls X, what does module Y depend on. Pass node for fast single-node lookup: returns type, file, depends_on, used_by. Pass both to get node detail + surrounding graph context together. Returns structured text within token_budget. Use before reading any files.

codegraph_contextA

Build a bounded, token-budgeted context subgraph for an AI coding task. Finds query-matching seed nodes, expands callers/dependencies/imports up to max_hops, ranks candidates, and returns compact nodes, relationship paths, budget usage, candidate counts, and per-item drop reasons.

codegraph_reportC

Return CODEGRAPH_REPORT.md — god nodes, clusters, surprising connections, suggested questions.

codegraph_nodesB

List all nodes of a given type, sorted by PageRank (most connected first).

codegraph_htmlA

Generate interactive vis.js HTML graph visualization. Dark theme, search box, community toggle, click-to-inspect node panel. Outputs codegraph-cache/graph.html. Also generates graph.graphml and obsidian/ vault.

codegraph_affectedA

BFS traversal: given a node name, find every node that would be affected if you change it — callers, importers, inheritors, etc. Use before refactoring to understand blast radius. Returns affected nodes with file paths, relation types, and traversal depth.

codegraph_filterA

Filter graph nodes by semantic properties. Results sorted by PageRank (most connected first). All filters optional — combine freely. node_type: function|class|module|file. exported/side_effect: bool. return_type: substring match. called_by/calls: node name. file_pattern: glob. token_budget: max tokens in response.

codegraph_archA

Return a module map: every file with its exported functions/classes and what it imports. Use this to understand project structure without reading any files. Call after codegraph_build. Much faster than reading each file.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 9 tools

Disambiguation4/5

Each tool has a clearly different job—build, query, contextualize, report, list, visualize, impact, filter, architectural map—but some overlap exists: codegraph_query and codegraph_context both return graph context, and codegraph_nodes is essentially a restricted version of codegraph_filter. The descriptions are strong enough that an agent can usually choose correctly.

Naming Consistency4/5

All tools share the consistent codegraph_ prefix and snake_case, and the suffixes are short and readable. However, they mix verb-style suffixes (build, query, filter) with noun-style suffixes (context, report, nodes, html, arch), so the set is not a strict verb_noun pattern.

Tool Count5/5

Nine tools is well within the ideal range and appropriate for a code-graph server. Each tool corresponds to a distinct workflow: building, querying, contextualizing, reporting, listing, visualizing, impact analysis, filtering, and architectural mapping.

Completeness5/5

The tool surface covers the full lifecycle of a code knowledge graph: build, inspect, filter, query, analyze impact, generate reports, and export visualization. There are no obvious missing operations that would block an agent from using the graph effectively; rebuild-on-change is handled via codegraph_build.

Maintenance

ActivityMaintained
ResponsivenessNo issues