Docs (voltagent) MCP Server

@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.

Trust grade
C
78/100
Last scanned
Trust
C · 78/100
How safe the published surface and source look. Deterministic; every point is auditable.
Capability
High
Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.
Coverage
Source
How much the scan could actually inspect. Shallow coverage is stated, never hidden.
C Why this grade 100 − 22 = 78/100

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:

PointsWhat was foundCategory
−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.

Findings 6

high Hardcoded JSON Web Token in server code (examples/with-voltagent-actions/src/config.ts)MTC-SRC-008

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

high Dynamic code execution in server code (examples/next-js-chatbot-starter-template/lib/tools/calculator.ts)MTC-SRC-001

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

high Dynamic code execution in server code (examples/with-playwright/src/tools/interactionTool.ts)MTC-SRC-001

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

medium Hardcoded egress to an external endpoint (examples/github-star-stories/src/tools.ts)MTC-SRC-003

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

medium Hardcoded egress to an external endpoint (examples/with-tavily-search/src/tools.ts)MTC-SRC-003

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

medium Hardcoded egress to an external endpoint (examples/with-whatsapp/src/webhooks/whatsapp.ts)MTC-SRC-003

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

What this scan could not see

Versions

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.

VersionScoreFindingsEngineScanned
v2.0.2 latest C 78/100 6 1.5.0 2026-07-22

Embed this score

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.

MCP Trust Score: C · 78/100
Markdown (GitHub README)
[![MCP Trust Score](https://mcptrustchecker.com/registry/voltagent-docs-mcp/badge.svg)](https://mcptrustchecker.com/registry/voltagent-docs-mcp)
HTML
<a href="https://mcptrustchecker.com/registry/voltagent-docs-mcp"><img src="https://mcptrustchecker.com/registry/voltagent-docs-mcp/badge.svg" alt="MCP Trust Score" height="20"></a>
Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/voltagent-docs-mcp/badge.json via https://img.shields.io/endpoint?url=…

Verify this score yourself

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

Use the free API → How scoring works

Other implementations of Docs 1

Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →

More in Learning & Documentation