ckg
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
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
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| locateA | Find where a feature or symbol lives in ONE call: ranked hits with their summaries, plus a source snippet of the top hit to confirm. Start here for "where is X" / "where do we do Y" — usually all you need; no setup call required first. |
| entry_pointA | Where does a feature BEGIN? Returns the entry/boundary that dominates the feature (route handler, CLI command, main, or exported API) — its file is where to start reading — plus the call path down through it. Use for "where do I start to understand X"; for "where is symbol X defined" use locate. |
| searchA | Hybrid (semantic + symbol) ranked summaries — NOT source. Returns several candidates without snippets; prefer |
| get_contextB | A node's generated summary/context (title, summary, description, signature, domain, keywords). Pass |
| get_sourceA | Raw source for a node — the deliberate 'expensive' read. |
| neighborsC | All adjacent nodes of an id, grouped by edge family (calls, imports, contains, related, …). |
| expandA | BFS up to k hops along ONE edge family (e.g. calls) from a node. |
| get_repo_mapA | The routing table: file/package summaries ranked by PageRank, packed to a token budget. Reach for it to orient on an unfamiliar repo. |
| pack_neighborhoodC | A node's k-hop dependency neighborhood, source packed in topological order to a token budget (the single-shot static fallback). |
| get_minimal_contextA | Optional ~100-token orientation: stats + the top nodes by importance. Call only if you want a quick lay of the land — it is NOT a prerequisite for the other tools. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose: locate finds definitions, entry_point finds starting points, search is hybrid, get_context retrieves summaries, get_source retrieves raw code, neighbors returns adjacent nodes, expand does BFS, get_repo_map gives an overview, pack_neighborhood packs dependency context, and get_minimal_context offers a quick orientation. No two tools are easily confused.
Tool names mostly follow a verb-based or get_ prefix pattern (locate, search, expand, get_context, get_source, get_repo_map). However, entry_point, neighbors, and pack_neighborhood deviate from the verb-first pattern, causing minor inconsistency. Still, all names are descriptive and lowercase.
With 10 tools, the server is well-scoped for navigating a code knowledge graph. Each tool serves a specific need in the exploration workflow, from quick lookup to deep context gathering, without redundancy.
The toolset covers major aspects of codebase exploration: finding symbols (locate), entry points (entry_point), searching (search), retrieving context/source (get_context, get_source), graph traversal (neighbors, expand), overview (get_repo_map), and packing context (pack_neighborhood). A minor gap might be a dedicated tool for listing all entry points or finding usages, but the existing tools largely compensate.