Agentsmcp MCP Server
agentsmcp
npm
v0.5.2
Published by ragavrida — 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.
Context-sync protocol for AI agents. Every agent has a mailbox.
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 − 7 = 93. 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 |
| −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 11
high Dynamic code execution in server code (ui/dist/assets/index-CkC-weU1.js)MTC-SRC-001
In the server's implementation (`ui/dist/assets/index-CkC-weU1.js:60`): 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: ypeof z!="function"&&(z=new Function(""+z));for(var A=new Array(arguments.length-1),O=0;O<A.length;O++)A[O]=arguments[O+
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 ui/dist/assets/index-CkC-weU1.js
high Shell/command execution in server code (dist/cli/github-login.js)MTC-SRC-002
In the server's implementation (`dist/cli/github-login.js:17`): 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: equire("crypto"); const child_process_1 = require("child_process"); const os_1 = require("os"); const DEFAULT_TIMEOUT_MS
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/cli/github-login.js
high Shell/command execution in server code (dist/cloud/auth.js)MTC-SRC-002
In the server's implementation (`dist/cloud/auth.js:81`): 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: esetMs; } async exec(fn) { if (this.isOpen) throw new CircuitOpenError(); try {
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/cloud/auth.js
high Shell/command execution in server code (dist/db-workers/harness.js)MTC-SRC-002
In the server's implementation (`dist/db-workers/harness.js:8`): 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: terWorkerHandler; const child_process_1 = require("child_process"); const fs_1 = require("fs"); exports.OP_CONNECT = "OP
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/db-workers/harness.js
high Shell/command execution in server code (dist/ingestion/connectors.js)MTC-SRC-002
In the server's implementation (`dist/ingestion/connectors.js:45`): 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: eSourcePath; const node_child_process_1 = require("node:child_process"); const promises_1 = require("node:fs/promises");
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/ingestion/connectors.js
medium Hardcoded egress to an external endpoint (dist/server.js)MTC-SRC-003
In the server's implementation (`dist/server.js:1071`): 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: const tokenRes = await fetch("https://github.com/login/oauth/access_token", { method: "POST
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/server.js
medium Dynamic module load from a non-literal (dist/distributed/worker.js)MTC-SRC-005
In the server's implementation (`dist/distributed/worker.js:187`): 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: -node/register"); } } require(modulePath); `; } function startWorker(port) { port.on("message", async (request) =>
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/distributed/worker.js
medium Dynamic module load from a non-literal (dist/mcp/index.js)MTC-SRC-005
In the server's implementation (`dist/mcp/index.js:87`): 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: try { require(indexerPath); } catch (e) { // Fallback: try tsx for develop
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.js
medium Dynamic module load from a non-literal (dist/modules/cognify/pipeline.js)MTC-SRC-005
In the server's implementation (`dist/modules/cognify/pipeline.js:63`): 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 parsed = results.require(exports.COGNIFY_TASK_IDS.parse); const embeddings = await context.config.embedde
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/modules/cognify/pipeline.js
medium Dynamic module load from a non-literal (dist/pipeline/eval-tasks.js)MTC-SRC-005
In the server's implementation (`dist/pipeline/eval-tasks.js:104`): 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: t parseOutput = results.require(exports.PARSE_COBOL_TASK_ID); const { SemanticElevator } = loadParserClasses();
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/pipeline/eval-tasks.js
low Shell/command execution in packaging/dev tooling (dist/scripts/index-codebase.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/index-codebase.js:58`): 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: e:crypto")); const node_child_process_1 = require("node: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/scripts/index-codebase.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 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 |
|---|---|---|---|---|
v0.5.2 latest |
A 93/100 | 11 | 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 agentsmcp --onlineMore in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology