Tanstack Ai MCP Server
@tanstack/ai-mcp
npm
v0.3.9
Source verified
Published by tanstack — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
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.
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 − 6 = 94. 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 |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
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 5
high Shell/command execution in server code (dist/bin/prettier-RSJS7CLU.js)MTC-SRC-002
In the server's implementation (`dist/bin/prettier-RSJS7CLU.js:15785`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ) { (function exec() { setTimeout(function() { if (editLength > maxEditLength || Dat
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/bin/prettier-RSJS7CLU.js
high Shell/command execution in server code (dist/bin/typescript-4QM2OYCL.js)MTC-SRC-002
In the server's implementation (`dist/bin/typescript-4QM2OYCL.js:7749`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: sync_hooks", "buffer", "child_process", "cluster", "console", "constants", "crypto", "dgram", "diagnostics_channel", "dn
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/bin/typescript-4QM2OYCL.js
medium Dynamic module load from a non-literal (dist/bin/bin.js)MTC-SRC-005
In the server's implementation (`dist/bin/bin.js:15268`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const mod = await jiti.import(tsPath); return mod.default; } if (existsSync(jsonPath)) { const { readFileSy
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/bin/bin.js
medium Dynamic module load from a non-literal (dist/bin/jiti-LBID3VGW.js)MTC-SRC-005
In the server's implementation (`dist/bin/jiti-LBID3VGW.js:3031`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: nativeImport = (id) => import(id); var _transform; function lazyTransform(...args) { if (!_transform) { _transfor
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/bin/jiti-LBID3VGW.js
medium Dynamic module load from a non-literal (dist/bin/prettier-RSJS7CLU.js)MTC-SRC-005
In the server's implementation (`dist/bin/prettier-RSJS7CLU.js:4234`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: parent).href); return import(url3); } function requireFromFile(id, parent) { const require22 = createRequire(parent)
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/bin/prettier-RSJS7CLU.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 10
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 |
|---|---|---|---|---|
v0.3.9 latest |
A 94/100 | 5 | 1.13.0 | 2026-09-07 |
v0.3.8 |
A 94/100 | 5 | 1.13.0 | 2026-09-01 |
v0.3.7 |
A 94/100 | 5 | 1.13.0 | 2026-08-28 |
v0.3.5 |
A 94/100 | 5 | 1.13.0 | 2026-08-27 |
v0.3.4 |
A 94/100 | 5 | 1.12.1 | 2026-08-24 |
Show 5 more versions ↓
v0.3.3 |
A 94/100 | 5 | 1.12.1 | 2026-08-22 |
v0.3.2 |
A 94/100 | 5 | 1.12.1 | 2026-08-20 |
v0.3.1 |
A 94/100 | 5 | 1.12.1 | 2026-08-19 |
v0.3.0 |
A 94/100 | 5 | 1.12.1 | 2026-08-18 |
v0.2.7 |
A 94/100 | 5 | 1.12.1 | 2026-08-10 |
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 @tanstack/ai-mcp --onlineOther implementations of Tanstack 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.
Ampersand AI SDK
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 Lifestyle & Local
MCP server for Australian address search and validation via Addressr
Admissions data & match scores for law, medical, dental, MBA, pharmacy, vet, optometry schools
Live AI data for agents: model releases, regulations (EU AI Act), GenAI glossary, daily news.
AirTreks MCP Server — complex flight routing intelligence for AI agents. Plan multi-city trips, validate alliance routings, get carrier recommendations, and create trip ideas.
Physician-reviewed medical opinions and prescriptions for AI agents.
Thin MCP server + CLI that proxy the atrium /api/v1 observability surface using an oc_live_ Bearer key. Talks HTTP only — no Convex imports.