@voltagent/docs-mcp
npm
v2.0.2
Published by @voltagent — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.
Every server starts at 100. These are the exact deductions the deterministic engine applied — each one reproducible, none of it an opinion or an LLM's guess:
| Points | What was found | Category |
|---|---|---|
| −22 | Hardcoded JSON Web Token in server code MTC-SRC-008 | exfiltration |
Grade capped: 1 confirmed high finding → grade capped at C. A hard gate overrides the point total — no amount of clean surface buys back a confirmed catastrophe.
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind the deduction.
A live-looking JSON Web Token is hardcoded in `examples/with-voltagent-actions/src/config.ts:66`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: JSON Web Token: eyJh…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server examples/with-voltagent-actions/src/config.ts
In the server's implementation (`examples/next-js-chatbot-starter-template/lib/tools/calculator.ts:24`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eval(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server examples/next-js-chatbot-starter-template/lib/tools/calculator.ts
In the server's implementation (`examples/with-playwright/src/tools/interactionTool.ts:94`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eval(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server examples/with-playwright/src/tools/interactionTool.ts
In the server's implementation (`examples/github-star-stories/src/tools.ts:13`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: fetch(`https://api.github.com/users/${username}`
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server examples/github-star-stories/src/tools.ts
In the server's implementation (`examples/with-tavily-search/src/tools.ts:63`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: fetch("https://api.tavily.com/search"
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server examples/with-tavily-search/src/tools.ts
In the server's implementation (`examples/with-whatsapp/src/webhooks/whatsapp.ts:13`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: fetch(`https://graph.facebook.com/v18.0/${phoneNumberId}/messages`
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server examples/with-whatsapp/src/webhooks/whatsapp.ts
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v2.0.2 latest |
C 78/100 | 6 | 1.5.0 | 2026-07-22 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @voltagent/docs-mcp --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
Security scan results for the Ab Integrations MCP server.
Security scan results for the Academic Research MCP server.
Security scan results for the Academic Research Mcp Suite MCP server.
Security scan results for the Adonis Docs MCP server.
Security scan results for the Adonis Mcp Docs MCP server.
Security scan results for the Advisor MCP server.