mcp-server@0.8.429
VERIFIED· startup onlyPublisher claims: "MCP server that gives AI assistants access to aVenture research data on companies, people, funding, and news." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
LANGFUSE_SECRET_KEYSENTRY_DSNConfiguration, not credentials: API_ENV, API_URL, AVENTURE_API_REQUEST_TIMEOUT_MS, AVENTURE_MCP_JSON_LIMIT, AVENTURE_MCP_PATH, AVENTURE_MCP_PORT, CLICOLOR_FORCE, GIT_SHA, LANGFUSE_BASE_URL, LANGFUSE_PUBLIC_KEY, OTEL_EXPORTER_OTLP_TRACES_ENDPOINT, SENTRY_RELEASE- Where it talks to
- aventure.vc (its own)Also status.invalid, placeholder.invalid — 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 status.invalid, placeholder.invalid as well as its own vendor. The guard injects LANGFUSE_SECRET_KEY, SENTRY_DSN only into requests to aventure.vc (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.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-13 and scored it 89/100 (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 · 20 s · 2 scenarios · 0 deviationsStatic findings
….hbase.namespace`,yt=`db.redis.database_index`,bt=`db.mongodb.collection`,xt=`db.sql.table`,St=`exception.type`,Ct=`exception.message`,wt=`exception.stacktrace`,Tt=`exception.escaped`,Et=`faas.trigger`,Dt=`faas.execution`,Ot=`faas.document…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…ery:p(),jsonBodyLimit:S,metricsScrapeSecret:C}).then(e=>{c({component:`aventure-mcp-server`,event:`server_listening`,fields:{port:b,path:x}}),process.stdout.write(`${i.bin[0]} listening at http://localhost:${b}${x}\n`);let t=t=>{if(w)retur…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.…=T(n);r!==void 0&&(t[e]=r)}super({exporter:e,...t})}};y(),Me();var gn=`aventure-mcp-server`,_n=`aventure=mcp`,vn=`langfuse.session.id`,yn=`/api/public/otel/v1/traces`,bn=5e3,xn=new Set([`langfuse.observation.input`,`langfuse.observation.ou…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.….stringify(t);a.append(e.name,new Blob([n],{type:`application/json`}),`${e.name}.json`)}else{let n=dr(a,e.name,t);if(!n.ok)return n}}}return p(`Multipart body prepared`,{body:a})}function or(e){if(typeof e==`object`&&e&&!Array.isArray(e)){…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…t{existsSync as o}from"node:fs";var s=`@aventurevc/aventure-cli`,c=`@aventurevc/mcp-server`,l=`aventure`,u=`https://registry.npmjs.org/`,d=[s,c,``,``];function f(e){let{entryPath:n,manifest:r,manifestPath:i,packageRoot:a}=t(e);return p(r,i…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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
No advisories in OSV for @aventurevc/mcp-server@0.8.429 as of 26 h ago. This is the package itself, not its dependencies.