Amp Labs Ai (amp-labs) MCP Server
@amp-labs/ai
npm
v0.1.0
Published by @amp-labs — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Ampersand AI SDK
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 4 = 96. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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 a deduction.
Findings 3
medium Hardcoded egress to an external endpoint (dist/mcp/index.cjs)MTC-SRC-003
In the server's implementation (`dist/mcp/index.cjs:1`): 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: ry{return i=await(await fetch("https://api.withampersand.com/v1/oauth-connect",{method:"POST",headers:{"Content-Type":"a
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 dist/mcp/index.cjs
medium Hardcoded egress to an external endpoint (dist/request-BUKZkneD.js)MTC-SRC-003
In the server's implementation (`dist/request-BUKZkneD.js:1`): 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: ectId:e})};return(await fetch("https://api.withampersand.com/v1/oauth-connect",n)).text()}async function x({provider:s,e
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 dist/request-BUKZkneD.js
medium Hardcoded egress to an external endpoint (dist/request-BfSotDPs.mjs)MTC-SRC-003
In the server's implementation (`dist/request-BfSotDPs.mjs:11`): 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: }) }; return (await fetch("https://api.withampersand.com/v1/oauth-connect", n)).text(); } async function u({ provi
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 dist/request-BfSotDPs.mjs
Tools 5
Each tool and what it can reach — statically extracted from the published source.
check-connectionno sensitive capabilitycheck-installationno sensitive capabilitycreate-installationno sensitive capabilitysend-requestno sensitive capabilitystart-oauthno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (5 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
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 |
|---|---|---|---|---|
v0.1.0 latest |
A 96/100 | 3 | 1.13.0 | 2026-09-07 |
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.
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 @amp-labs/ai --onlineOther implementations of Amp Labs Ai 7
Independent packages implementing the same tool, scanned with the same engine. Compare all 8 side by side →
Theia - MCP Integration
Crossdeck AI — the MCP connector that lets Claude, Cursor, and any AI tool query and operate your Crossdeck app. The product is 'Crossdeck understands your app'; MCP is just the transport.
Bridge between @gemstack/ai-sdk Agents and Model Context Protocol servers: consume remote MCP tools as Agent tools, and expose an Agent as an MCP server.
Host-side Model Context Protocol client for TanStack AI: discover and run MCP server tools, resources, and prompts in any adapter's chat() loop, with generated end-to-end types.
Local MCP bridge: unify multi-endpoint model capabilities into a single MCP server + CLI + Web UI
本地 MCP 橋樑：把多個 API key + endpoint 收編為統一的模型能力池，給 Agent 透過 MCP 調用
More in Other
A Model Context Protocol server implementation for AdGuard Home that enables AI agents to query and manage DNS records, filtering rules and more
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
MCP server with Airtable integration
A free one-minute reset for people, delivered by AI, with no account or personal data.
Access SEC filings efficiently, save time and tokens, and get cited answers.
A smart [MCP](https://modelcontextprotocol.io) server for [AniList](https://anilist.co) that gets your anime/manga taste - not just API calls.