mcp-server@4.14.0
CAUTIONPublisher claims: "MCP server for interacting with Runpod API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Started with a decoy RUNPOD_API_KEY; tool list observed. Tool calls with a real credential not tested.- Tested
- server startup with a tagged decoy in RUNPOD_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with a real credential
- Needs
- RUNPOD_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.
Before you give it your token
- It will ask for
ALP_SINK_SECRETAPI_KEYS_URLMCP_SKIP_CREDENTIAL_CHECKPOSTHOG_API_KEYRUNPOD_API_KEYRUNPOD_ASSISTANT_API_KEYRUNPOD_AUTHED_GRAPHQL_URLConfiguration, not credentials: ALP_SINK_URL, CLAUDE_CONFIG_DIR, ID_PATTERN, KNOWLEDGE_HIDDEN_RULES, KNOWLEDGE_SEARCH_URL, MCP_ANALYTICS_SALT, MCP_REQUEST_LOG_SAMPLE_RATE, MCP_SCHEMA_VALIDATION, MCP_VERBOSE_LOGS, PI_CODING_AGENT_DIR, POSTHOG_HOST, RUNPOD_API_BASE_URL, RUNPOD_MCP_URL, RUNPOD_PUBLIC_GRAPHQL_URL, RUNPOD_SERVERLESS_API_URL, VERCEL- Where it talks to
- runpod.io, runpod.ai (its own)Also posthog.com — 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
- what the tools do when called with a real credential
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names posthog.com as well as its own vendor. The guard injects ALP_SINK_SECRET, API_KEYS_URL, MCP_SKIP_CREDENTIAL_CHECK, POSTHOG_API_KEY, RUNPOD_API_KEY, RUNPOD_ASSISTANT_API_KEY, RUNPOD_AUTHED_GRAPHQL_URL only into requests to runpod.io (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 4.12.0
vet-skills diff mcp-server 4.12.0 4.14.0In the sandbox, this version reached for nothing 4.12.0 did not. Compared from the two recorded runs, not from source.
Only one of the two runs produced a tool list; tools are not compared.
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) on 2026-11-20 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Credential pass-through configuration; Tool description instructs the agent: credential exfiltration instruction; References a credential file in the home directory. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 56 s · 2 scenarios · 0 deviationsStatic findings
throw new Error("runpod: API key required (set RUNPOD_API_KEY or pass apiKey)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…xpose, use the machine-readable OpenAPI spec at https://api.runpod.io/v2/openapi.json or the API reference at https://docs.runpod.io/api-reference-v2/overview. Prefer the MCP tools for reads because their results redact secret environment …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own." npx @runpod/mcp-server@latest add --list list clients, whether each is detected, and its config file",Fix: Pin versions and sources; vendor anything fetched at install time.ret-looking values as [redacted]: never send that placeholder back, it would overwrite the secret with the literal string. Supply the real value or a {{ RUNPFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.To run it without prompts, name the clients: npx @runpod/mcp-server@latest ${subcommand} --client <ids>Fix: Pin versions and sources; vendor anything fetched at install time.…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own." npx @runpod/mcp-server@latest add [--client <ids>] configure your agents (see add --help)",Fix: Pin versions and sources; vendor anything fetched at install time." npx @runpod/mcp-server@latest add interactive setup (needs a terminal)",Fix: Pin versions and sources; vendor anything fetched at install time.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.pattern: "^[\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]*[Rr][Uu][Nn][Pp][Oo][Dd]:"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.pattern: "^[\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]*[Rr][Uu][Nn][Pp][Oo][Dd]:"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own." npx @runpod/mcp-server@latest add --client <ids> no prompts: configure these clients",Fix: Pin versions and sources; vendor anything fetched at install time." npx @runpod/mcp-server@latest remove --client <ids> no prompts: remove Runpod from them",Fix: Pin versions and sources; vendor anything fetched at install time.…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.throw new Error("runpod: API key required (set RUNPOD_API_KEY or pass apiKey)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.throw new Error("runpod: API key required (set RUNPOD_API_KEY or pass apiKey)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own." npx @runpod/mcp-server@latest remove --client <ids> remove Runpod from your agents"Fix: Pin versions and sources; vendor anything fetched at install time.…xpose, use the machine-readable OpenAPI spec at https://api.runpod.io/v2/openapi.json or the API reference at https://docs.runpod.io/api-reference-v2/overview. Prefer the MCP tools for reads because their results redact secret environment …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pattern: "^[\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]*[Rr][Uu][Nn][Pp][Oo][Dd]:"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…xpose, use the machine-readable OpenAPI spec at https://api.runpod.io/v2/openapi.json or the API reference at https://docs.runpod.io/api-reference-v2/overview. Prefer the MCP tools for reads because their results redact secret environment …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why." RUNPOD_API_KEY=<key> npx @runpod/mcp-server@latest run the MCP server over stdio",Fix: Pin versions and sources; vendor anything fetched at install time.pattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]",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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim runpod: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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.
- 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.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- Unicode escape sequence 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.