mcp-behave@0.3.0
CAUTION· startup onlyPublisher claims: "Runtime behavioral auditor for MCP servers — scope-violation detection via native interposition & syscall tracing" 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: 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
MCP_BEHAVE_TOKENConfiguration, not credentials: MCP_BEHAVE_CALL_TIMEOUT, MCP_BEHAVE_DASHBOARD_URL, MCP_BEHAVE_DEBUG, MCP_BEHAVE_STATE_DIR, OUT_DIR, PROBE_NOISE_EXTRA, TRACE_FILE- Where it talks to
- no vendor host named in the codeAlso python.org, astral.sh, githubusercontent.com, modelcontextprotocol-security.io, attacker-c2.example — 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 python.org, astral.sh, githubusercontent.com, modelcontextprotocol-security.io, attacker-c2.example as well as its own vendor. The guard injects MCP_BEHAVE_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 0.1.3
vet-skills diff mcp-behave 0.1.3 0.3.0This version reaches for something 0.1.3 did not: 5 new hosts (astral.sh, attacker-c2.example, githubusercontent.com, modelcontextprotocol-security.io, …) · 1 new credential variable (MCP_BEHAVE_TOKEN) · 2 new credential files (~/.env, ~/.ssh/id_rsa). Compared from the two recorded runs, not from source.
- New hosts
- astral.sh, attacker-c2.example, githubusercontent.com, modelcontextprotocol-security.io, python.org
- New credential variables
- MCP_BEHAVE_TOKEN
- New credential files
- ~/.env, ~/.ssh/id_rsa
0.1.3 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; startup only; authenticated tool behavior not tested) on 2026-11-18 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Privileged sudo command; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 20 s · 2 scenariosStatic findings
RUN curl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."/.env*",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.the server. This runs as YOU -- no sudo needed. Two things can prevent it:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# canary files in ./sandbox_home are used as ~/.ssh, ~/.env, etc.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.with open(os.path.expanduser("~/.ssh/id_rsa")) as f: # reads a secretFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".netrc", "/etc/shadow", ".kube", ".docker/config")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.".env", "id_rsa", "id_ed25519", ".ssh", ".aws", ".kube", "/etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.SENSITIVE = (".ssh", "id_rsa", "id_ed25519", ".env", ".aws", "credentials",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run([cc, "-shared", "-fPIC", "-O2", "-o", so, src, "-ldl"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."/etc/shadow", ".npmrc", ".git/config", "credentials", "secrets",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.with open(os.path.expanduser("~/.ssh/id_rsa")) as f: # reads a secretFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run([cc, *arch_flags, "-dynamiclib", "-O2",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.with open(os.path.expanduser("~/.ssh/id_rsa")) as f: # reads a secretFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.("../../../../../../../../etc/passwd", -1),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.out = subprocess.run([cs, "-d", "--verbose=4", path],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.elif any(sens in arg_norm for sens in ("/.ssh", "/.aws", "/.kube", "/.gnupg", "/etc/shadow")):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# server directly, not a uvx/npx downloader. Tracing through uvx/npx pollutesFix: Pin versions and sources; vendor anything fetched at install time.("HIGH", "read a sensitive path: ~/.ssh/id_rsa"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert sarif.classify_rule_id("HIGH", "read a sensitive path: ~/.ssh/id_rsa") == "MCP002"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f"leaky server's ~/.ssh/id_rsa read was not detected. findings: {findings}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.server's ~/.ssh/id_rsa read hits something."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert sarif.classify_rule_id("HIGH", "read a sensitive path: ~/.ssh/id_rsa") == "MCP002"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.("HIGH", "read a sensitive path: ~/.ssh/id_rsa"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."args": ["-y", "@modelcontextprotocol/server-filesystem", "/", "~/.ssh"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.server's ~/.ssh/id_rsa read hits something."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Unpinned remote package execution (e.g. npx without version tag).Fix: Pin versions and sources; vendor anything fetched at install time.f"leaky server's ~/.ssh/id_rsa read was not detected. findings: {findings}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- Direct prompt injection patterns (e.g., `Ignore previous instructions`, `SYSTEM PROMPT:`, `<system>`, `[system instruction]`, `you must always call this tool first`).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.assert any("../../../../../../../../etc/passwd" in f.get("path", "") for f in fuzz_sets)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.{"severity": "HIGH", "message": "read a sensitive path: ~/.ssh/id_rsa"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."`python -m mcp_server_fetch`). For --transport sse/"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."uri": "file:///app/config/.env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.[!] HIGH prompt injection pattern detected in tool 'notes_analyzer' description: 'Ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.{"severity": "HIGH", "message": "read a sensitive path: ~/.ssh/id_rsa"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.(home / ".env").write_text("CANARY_SECRET=canary\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Direct prompt injection patterns (e.g., `Ignore previous instructions`, `SYSTEM PROMPT:`, `<system>`, `[system instruction]`, `you must always call this tool first`).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.help="Path to manifest.json, tools.json, output directory, or '-' for stdin (default: stdin).",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.{"severity": "HIGH", "message": "read a sensitive path: ~/.ssh/id_rsa"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.RUN curl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.("HIGH", "read a sensitive path: ~/.ssh/id_rsa"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert sarif.classify_rule_id("HIGH", "read a sensitive path: ~/.ssh/id_rsa") == "MCP002"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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Reads credential paths from the home directory≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim navid72m: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- 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.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.