context7-mcp@4.7.3
VERIFIEDPublisher claims: "MCP server for Context7" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
Before you give it your token
- It will ask for
AUTH_CHECK_PATHAUTH_SERVER_URLCONTEXT7_API_KEYMCP_AUTH_ENFORCEMENTMCP_OAUTH_ALLOWED_AUDIENCESMCP_OAUTH_AUDIENCE_ENFORCEMENTMCP_OAUTH_TOKEN_VALIDATIONOAUTH_AUTH_SERVER_URLOAUTH_JWKS_URLOPENAI_APPS_CHALLENGE_TOKENConfiguration, not credentials: CONTEXT7_API_URL, CONTEXT7_EXPERIMENTAL, CONTEXT7_RESEARCH_PREVIEW, EMA_ISSUER, EMA_JWKS_URL, MCP_CLIENT_IP_ASSERTION_KEY, NODE_EXTRA_CA_CERTS, RESOURCE_URL, SNAPSHOT_PATH, VERCEL_MARKETPLACE_OIDC_AUDIENCE, VERCEL_MARKETPLACE_OIDC_ISSUER- Where it talks to
- no vendor host named in the codeAlso context7.com, microsoftonline.com, x.example, vercel.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
- 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 context7.com, microsoftonline.com, x.example, vercel.com as well as its own vendor. The guard injects AUTH_CHECK_PATH, AUTH_SERVER_URL, CONTEXT7_API_KEY, MCP_AUTH_ENFORCEMENT, MCP_OAUTH_ALLOWED_AUDIENCES, MCP_OAUTH_AUDIENCE_ENFORCEMENT, MCP_OAUTH_TOKEN_VALIDATION, OAUTH_AUTH_SERVER_URL, OAUTH_JWKS_URL, OPENAI_APPS_CHALLENGE_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 4.7.0
vet-skills diff context7-mcp 4.7.0 4.7.3In the sandbox, this version reached for nothing 4.7.0 did not. Compared from the two recorded runs, not from source.
Tool descriptor hashes were not recorded for both runs; renamed or added tools are compared, rewritten descriptions are not.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-17 and scored it 85/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 56 s · 2 scenarios · 0 deviationsStatic findings
? `npx ctx7 setup ${flag} --mcp${transportFlag} -y`Fix: Pin versions and sources; vendor anything fetched at install time.<summary><b>Install in Amp</b></summary> Run this command in your terminal. See [Amp MCP docs](https://ampcode.com/manual#mcp) for more info. #### With OAuth ``Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."build": "tsc && chmod 755 dist/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.<summary><b>Install in Claude Code</b></summary> Run this command. See [Claude Code MCP docs](https://docs.anthropic.com/en/docs/claude-code/mcp) for more info.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.: `npx ctx7 setup --mcp${transportFlag}`;Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
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
Not checked against OSV yet; the weekly check has not reached this version.