io.github.James-Chahwan/repo-graph
PYPI · MCP-REPO-GRAPH · SCANNED SEP 20
Structural graph map of any codebase so LLMs navigate by structure, not guesswork.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1521 tokens (~253/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management17
- Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the io.github.James-Chahwan/repo-graph MCP server?
io.github.James-Chahwan/repo-graph runs locally as a PyPI package, launched with uvx mcp-repo-graph. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mcp-repo-graph
claude mcp add james-chahwan-repo-graph -- uvx mcp-repo-graph
{
"mcpServers": {
"james-chahwan-repo-graph": {
"command": "uvx",
"args": [
"mcp-repo-graph"
]
}
}
} {
"servers": {
"james-chahwan-repo-graph": {
"command": "uvx",
"args": [
"mcp-repo-graph"
]
}
}
} codex mcp add james-chahwan-repo-graph -- uvx mcp-repo-graph
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"james-chahwan-repo-graph": {
"type": "local",
"command": [
"uvx",
"mcp-repo-graph"
],
"enabled": true
}
}
} openclaw mcp add james-chahwan-repo-graph --command uvx --arg mcp-repo-graph
mcp_servers:
james-chahwan-repo-graph:
command: "uvx"
args: ["mcp-repo-graph"] {
"McpServers": {
"james-chahwan-repo-graph": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"mcp-repo-graph"
]
}
}
} assistant mcp add james-chahwan-repo-graph -t stdio -c uvx -a mcp-repo-graph
{
"mcpServers": {
"james-chahwan-repo-graph": {
"command": "uvx",
"args": [
"mcp-repo-graph"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +2
- Security disclosure: unverified → fail ▼ functional
- Stability: unverified → 0.17 ▲ functional
- MCP protocol: Implements a current MCP spec version (2026-07-28). functional
- Package version: 0.4.21 → 0.5.1 functional
- 19 Sept 26 0
- Security disclosure: fail → unverified ▼ functional
- 17 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 16 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Sept 26 +31
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Schema quality: excellent functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 100 functional
- First check of Tool coverage: 100 functional
- Package version: 0.4.20 → 0.4.21 functional
- 14 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 12 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 11 Sept 26 −15
- Malware scan: pass → unverified ▼ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/mcp-repo-graph@0.5.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 31 packages
| Packages resolved | 31 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
find ~249
Turn any text into the ranked nodes that matter — the on-ramp to the graph. A symbol or keyword returns matching nodes; a pasted stacktrace / failing-test id / diff is resolved to the code it implicates and ranked by relevance. Set `expand=true` to fan out to the surrounding neighbourhood (spreading activation). Every row carries `path:line`, so `read` the top hits directly — no grep.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | Max chars in the result. 0 = no cap. |
| expand | boolean | – | Return the relevant neighbourhood (Personalized-PageRank ranked) around the matches, not just the matches themselves. Use to discover what surrounds a seed. |
| kind | string | – | Force the signal type: 'symbol', 'stacktrace', 'test', 'diff', or 'auto' (sniff the shape). |
| query | string | yes | What to locate: a symbol/keyword (e.g. `User`, `checkout`), OR a failure signal — paste a raw stacktrace, a failing-test id (path::test), or a unified diff / changed-file list. |
| top_k | integer | – | Max results. Default 20. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
impact ~290
Blast radius in one call: fan out from one or more nodes to everything they affect (forward) or depend on / are used by (backward), returned as a complete, deduped, Personalized-PageRank-ranked, located closure. Each row carries `path:line`, the edge `via` reason it's in scope, and a `⊘` when the engine finds it unreachable from any entry point (likely dead). Structural import/containment fan-out is excluded — no noise. Depth-1 in both directions is a node's immediate neighbours. Pass several comma-separated nodes to assess a whole diff at once.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | Max chars in the result. 0 = no cap. |
| depth | integer | – | How many hops to fan out. Default 4. |
| direction | string | – | 'forward' (what it affects), 'backward' (what it depends on / who uses it), or 'both'. (Aliases: downstream=forward, upstream=backward.) |
| live_only | boolean | – | Drop nodes not reachable from any entry point (likely-dead code). Default False = show all, marking dead ones ⊘. |
| nodes | string | yes | One or more node names/qnames, comma-separated. A diff touching N symbols is one call. |
| top_k | integer | – | Cap the ranked result. 0 = no cap. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
orient ~209
Get the lay of the land — ALWAYS the first call on a codebase. With no arguments: a counts + entry-points overview plus a `blind spots` note flagging which (language, edge-kind) extractions are partial so you know where to fall back to grep. With `seed=<node>`: the dense structural map scoped to that node's neighbourhood. With `full=true`: the whole-repo dense map (the full context dump). Orient first, then `find` to jump to nodes, `impact` for blast radius, `trace` for flows.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | Max chars in the result. 0 = default cap (~50k for the full map, uncapped otherwise). |
| full | boolean | – | With no seed: return the whole-repo dense structural map instead of the counts overview. Ignored when seed is given. |
| seed | string | – | Optional node/qname to scope the map around (its activated neighbourhood). Blank = repo overview. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
read ~207
Return the source code for one or more nodes, sliced from their files by the graph's line spans. Use after `find`/`impact` to read the exact code without grepping — comma-separate several node names to read the whole ranked set in a single call. Each node is a code block headed by its qname and `path:start-end`, plus a `context:` footer with structural facts the source alone doesn't show: HTTP method, cross-stack callers, covering tests, and intent/decision/constraint cells when present.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | Max chars in the result (shared across all nodes when several are given). 0 = no cap. |
| context_lines | integer | – | Lines of padding above and below the node's span. Default 0. |
| node | string | yes | Node name or qname to read. Comma-separate several (e.g. the top-ranked nodes from `find`/`impact`) to slice them all in one call. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
refresh ~194
(Re)build the structural graph with tree-sitter AST parsing across 20 languages, running the cross-stack resolvers (HTTP, gRPC, GraphQL, WebSocket, queues, events, CLI). Incremental by default — only changed files re-parse — so it's cheap to call after edits; set `full=true` to force a clean reparse. Accepts a local path or a git URL (cloned on demand). Call after a major refactor; routine edits are picked up automatically by the file watcher.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | Force a full reparse instead of reusing the per-file parse cache. Default False (incremental — only changed files re-parse, so this is cheap after edits). |
| repo_path | string | – | Path or git URL to (re)scan. Blank = the repo the server is serving. A different path/URL retargets the server at it. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
trace ~197
Follow the code across boundaries. One argument: trace a feature end-to-end — the ordered path from entry through the stack, each hop labelled with its mechanism (call / HTTP / queue / event / data), crossing service boundaries (frontend→backend). Two arguments: the shortest path between two specific nodes, hop by hop. This is where the graph beats reading many files — it knows the cross-stack links grep can't see.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | Max chars in the result. 0 = no cap. |
| depth | integer | – | Max hops for the cross-stack feature trace. Default 6. |
| from_node | string | yes | A feature/keyword to trace end-to-end (one arg), OR the start node when tracing a path to `to_node`. |
| to_node | string | – | Optional target node. Given → shortest path from_node→to_node. Blank → trace `from_node` as a feature across the stack. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
What is the io.github.James-Chahwan/repo-graph MCP server?
io.github.James-Chahwan/repo-graph is an MCP server listed in the public MCP registry as io.github.James-Chahwan/repo-graph. Structural graph map of any codebase so LLMs navigate by structure, not guesswork. This page covers its PyPI package (mcp-repo-graph).
Is the io.github.James-Chahwan/repo-graph MCP server safe to use?
io.github.James-Chahwan/repo-graph scores 49 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.James-Chahwan/repo-graph MCP server expose?
io.github.James-Chahwan/repo-graph exposes 6 tools: orient, find, impact, trace, read, refresh. Their descriptions and schemas cost roughly 1,346 tokens of context every time the server is loaded.
Is the io.github.James-Chahwan/repo-graph MCP server still maintained?
io.github.James-Chahwan/repo-graph is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.