fastmcp-slim@4.2.3
VERIFIED· not startedPublisher claims: "The dependency-slim FastMCP package." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso gofastmcp.com, prefect.io, esm.sh, your-domain.com, my-server.com, agentskills.io — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 4.1.4
vet-skills diff fastmcp-slim 4.1.4 4.2.3This version reaches for something 4.1.4 did not: 1 new host (agentskills.io). Compared from the two recorded runs, not from source.
- New hosts
- agentskills.io
4.1.4 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
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; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 80/100 (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 · 0 s · 2 scenarios · 0 deviationsStatic findings
return "npx" # On Unix-like systems, just use npxFix: Pin versions and sources; vendor anything fetched at install time.process = subprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.run(cmd, check=True, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."[dim]Use --format \\[fastmcp|mcp] for complete JSON output[/dim]"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.process = subprocess.run(cmd, check=True, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# cleanup can kill the subprocess even if the bundle fetch raises.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.help="Stdio command to connect to (e.g. 'npx -y @mcp/server')",Fix: Pin versions and sources; vendor anything fetched at install time.# Force kill the entire process groupFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.fastmcp list --command 'npx -y @mcp/server' --resourcesFix: Pin versions and sources; vendor anything fetched at install time.def _run_server(mcp_server: FastMCP, transport: Literal["sse"], port: int) -> None:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# If it's still alive, then force kill itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."""Get the correct npx command for the current platform."""Fix: Pin versions and sources; vendor anything fetched at install time.# MCPServer has no run-time `log_level` kwarg. Its HTTP runners passFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.# Own process group so _terminate_process can kill the whole treeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ENV_FILE = os.getenv("FASTMCP_ENV_FILE", ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.fastmcp project prepare myserver.json --output-dir ./prepared-envFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."npx not found. Please ensure Node.js and npm are properly installed "Fix: Pin versions and sources; vendor anything fetched at install time.subprocess.run([cmd, "--version"], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# Get the correct npx commandFix: Pin versions and sources; vendor anything fetched at install time."npx not found. Please ensure Node.js and npm are properly installed "Fix: Pin versions and sources; vendor anything fetched at install time.help="Stdio command to connect to (e.g. 'npx -y @mcp/server')",Fix: Pin versions and sources; vendor anything fetched at install time.app = mcp_server.http_app(transport="sse")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
Not checked against OSV yet; the weekly check has not reached this version.