bowerbird-mcp@2.1.1
CAUTION· not startedPublisher claims: "Manage knowledge, retrieve it, and verify it: keyword and semantic search over Markdown, ADR and MADR, OKF, SKOS and AsciiDoc (ADOC), and a human review (seal) bound to the exact text. An MCP server and CLI." 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 codeAlso postgresql.org, schemastore.org — 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
- 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 2026-11-18 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; 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
--8<-- [start:run]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# Your id, prefilled in confirmation prompts. Personal: prefer KB_USER in .env (git user.email is the fallback).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.SHARED_ONLY = {"format", "seal"} # what the folder is, and who must review it: only kbmcp.yaml sets these, never .env or the environmentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# or set KB_* environment variables; the environment wins over .env, and .env wins over this file, except for `format`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.name one with `--config`, so a server needs no env block. A `kbmcp.yaml` in a folder below the root overrides theFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.self.p = subprocess.Popen(["git", "cat-file", "--batch"], cwd=top, stdin=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.g = subprocess.run(["git", "-C", str(KB_ROOT), "ls-files", "-co", "--exclude-standard", "-z", "--", f":(glob)**/{CONFIG}"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.--8<-- [end:run]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.return subprocess.run(["git", "-c", "core.quotePath=false", *a], cwd=cwd, capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# uncomment a line to change it. Personal or machine settings do not go here: copy env.example to .env (not committed)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 bowerbird-mcp@2.1.1 as of 2 min ago. This is the package itself, not its dependencies.
What would make this Verified
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim dfoulks1: 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.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.