Grasp (ashfordeOU) MCP Server

grasp-mcp-server npm v3.21.0 Source verified

Published by ashfordeou — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.

Trust grade
A
94/100
Last scanned
Trust
A · 94/100
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.
A Why this grade 100 − 6.3 = 94/100

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
−6.3 Unsafe deserialization MTC-SRC-007 permissions

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 7

high Dynamic code execution in server code (dist/parser.js)MTC-SRC-001

In the server's implementation (`dist/parser.js:540`): 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 dist/parser.js

high Shell/command execution in server code (dist/analyzer.js)MTC-SRC-002

In the server's implementation (`dist/analyzer.js:4150`): 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: child_process

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/analyzer.js

high Shell/command execution in server code (dist/parser.js)MTC-SRC-002

In the server's implementation (`dist/parser.js:548`): 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: child_process

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/parser.js

medium Hardcoded egress to an external endpoint (dist/parser.js)MTC-SRC-003

In the server's implementation (`dist/parser.js:1739`): 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.osv.dev/v1/querybatch'

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/parser.js

medium Dynamic module load from a non-literal (dist/parser.js)MTC-SRC-005

In the server's implementation (`dist/parser.js:623`): 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: __import__(

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/parser.js

medium Dynamic module load from a non-literal (dist/tree-sitter/bundle.js)MTC-SRC-005

In the server's implementation (`dist/tree-sitter/bundle.js:109`): 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: require(entry.nodeModule)

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/tree-sitter/bundle.js

medium Unsafe deserialization (dist/parser.js)MTC-SRC-007

In the server's implementation (`dist/parser.js:610`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: pickle.load(

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/parser.js

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
v3.21.0 latest A 94/100 7 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: A · 94/100
Markdown (GitHub README)
[![MCP Trust Score](https://mcptrustchecker.com/registry/grasp-mcp-server/badge.svg)](https://mcptrustchecker.com/registry/grasp-mcp-server)
HTML
<a href="https://mcptrustchecker.com/registry/grasp-mcp-server"><img src="https://mcptrustchecker.com/registry/grasp-mcp-server/badge.svg" alt="MCP Trust Score" height="20"></a>
Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/grasp-mcp-server/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 grasp-mcp-server --online

Use the free API → How scoring works

Other implementations of Grasp 1

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

More in AI, Memory & Reasoning