mcp-tollbooth@0.4.0
CAUTION· not startedPublisher claims: "A security gateway for AI agents: a transparent MCP proxy that enforces policy, DLP, and audit on every tool call and result." 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: Caution 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 code
- What the honeypot saw
- 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.
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 2026-11-10 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
<summary>Prefer text? The same run, line by line.</summary> ```console $ tollbooth hook pre < curl-pipe-sh.json # agent pipes a remote script to a shell ⛔ deny Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.r"(\.ssh/id_[a-z0-9_]+\b(?!\.pub)|\.aws/credentials|\.env\b(?!\.(example|sample|template))"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.r"|(^|/)\.env(\.(?!example$|sample$|template$)[A-Za-z0-9_-]+)?$"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.r"|\.netrc|\.pgpass|\.kube/config)",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Reading a credential file (SSH key, AWS creds, .env, ...).",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary>Advanced: wire a client by hand</summary> ```bash # Bootstrap a gateway config from an existing client config (or start from examples/tollbooth.yaml) tFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."Running a downloaded script: curl|sh, sh -c \"$(curl ...)\", bash <(curl ...).",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r"|/\.netrc$|/\.pgpass$|/\.docker/config\.json$|/\.kube/config$)",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 mcp-tollbooth@0.4.0 as of 4d ago. This is the package itself, not its dependencies.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim realgagenichols: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.