prefect-mcp@0.0.1b13
CAUTION· not startedPublisher claims: "MCP server for interacting with Prefect" 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
OPENAI_API_KEYTURBOPUFFER_API_KEYor--client-secretConfiguration, not credentials: ENVIRONMENT, EVALUATOR_MODEL, MODEL_PROVIDER, PREFECT_MCP_PUBLIC_BASE_URL, REASONING_AGENT_MODEL, SIMPLE_AGENT_MODEL, TURBOPUFFER_REGION- Where it talks to
- prefect.cloud, prefect.io, prefect.dev (its own)Also sitemaps.org, fastmcp.app — 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 with a scoped credential, under the guard, and read the third-party hosts first. The code names sitemaps.org, fastmcp.app as well as its own vendor. The guard injects OPENAI_API_KEY, TURBOPUFFER_API_KEY only into requests to prefect.cloud (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; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 76/100 (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>Setup and testing</summary> ```bash # clone the repo gh repo clone prefecthq/prefect-mcp-server && cd prefect-mcp-server # install dev deps and pre-comFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.env_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.sudo mv mcp-publisher /usr/local/bin/Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.load_dotenv(".env.local")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."prefect_mcp_server._prefect_client.client.httpx.BasicAuth"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."prefect_mcp_server.middleware.get_http_headers"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.env_prefix="LOGFIRE_", extra="ignore", env_file=".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from pydantic_ai.mcp import MCPServer, MCPServerStdio, MCPServerStreamableHTTPFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."prefect_mcp_server.middleware.get_http_headers"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.<summary>Cloud OAuth configuration reference</summary> Cloud OAuth settings use the `PREFECT_MCP_CLOUD_` prefix: | Environment variable | Purpose | | --- | --- Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.model_config = SettingsConfigDict(env_file=[".env"], extra="ignore")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."prefect_mcp_server.middleware.get_http_headers"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.env_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."prefect_mcp_server.middleware.get_http_headers"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.return MCPServerStreamableHTTP(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.env_prefix="PREFECT_DOCS_MCP_", extra="ignore", env_file=".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.process = subprocess.Popen(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.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 prefect-mcp@0.0.1b13 as of 2 h ago. This is the package itself, not its dependencies.
What would make this Verified
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim prefect-technologies-help: 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.
- Privileged sudo command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
- Python subprocess execution detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.