Skills/npm/mcp-server

mcp-server@1.8.38

VERIFIED· startup only

Publisher claims: "Model Context Protocol server for Graphite Atlas" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher graphite-atlas · publishing for 303 daysInstalls 2,426Last detonated 5d ago
$claude mcp add mcp-server -- npx -y @graphite-atlas/mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
GRAPHITE_ACCESS_TOKENConfiguration, not credentials: ATLAS_MCP_PROFILE, ATLAS_SCENARIO_ID, GRAPHITE_API_URL, MCP_TRANSPORT, NEXT_RUNTIME, VERCEL
Where it talks to
graphiteatlas.com (its own)Also memgraph.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names memgraph.com as well as its own vendor. The guard injects GRAPHITE_ACCESS_TOKEN only into requests to graphiteatlas.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets GRAPHITE_ACCESS_TOKEN=graphiteatlas.com -- npx -y @graphite-atlas/mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-09 and scored it 92/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 32 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
12sprocessdependency install exit 0
32sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-BWmTPM/task/home/work/acme-api/.claude/skills/mcp-server/dist/tools/annotations.js' } Node.js v22.23.4
32sprocessscript backend runs setup only
32sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/is-entrypoint.js:10 · npx invocation of non-well-known package — may execute untrusted code* The comparison has to survive symlinks. npm and npx install a package's binFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:394 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file… atlas <id> and save it to CLAUDE.md" ``` Claude will call `generate_setup` and write a `CLAUDE.md` file that combines the atlas brief with tool usage instructions. Future sessio…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/is-entrypoint.d.ts:13 · npx invocation of non-well-known package — may execute untrusted code* silently for every npx and every global install.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/is-entrypoint.js:15 · npx invocation of non-well-known package — may execute untrusted code* silently for every npx and every global install.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/is-entrypoint.ts:16 · npx invocation of non-well-known package — may execute untrusted code* silently for every npx and every global install.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/is-entrypoint.ts:11 · npx invocation of non-well-known package — may execute untrusted code* The comparison has to survive symlinks. npm and npx install a package's binFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/is-entrypoint.d.ts:8 · npx invocation of non-well-known package — may execute untrusted code* The comparison has to survive symlinks. npm and npx install a package's binFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/prompts.ts:176 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file8. WRITE TO CLAUDE.MD — After the user approves, APPEND (do not overwrite) the snippet to the project's CLAUDE.md file. If no CLAUDE.md exists, create one.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/prompts.js:162 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file8. WRITE TO CLAUDE.MD — After the user approves, APPEND (do not overwrite) the snippet to the project's CLAUDE.md file. If no CLAUDE.md exists, create one.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈51 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for @graphite-atlas/mcp-server@1.8.38 as of 5d ago. This is the package itself, not its dependencies.