Agr Mcp Server Enhanced MCP Server
agr-mcp-server-enhanced
npm
v3.2.6
Published by nuin — 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.
Enhanced Alliance of Genome Resources MCP Server - High-performance JavaScript implementation with Node v23 compatibility
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 Shell/command execution in server code (bin/agr-chat.js)MTC-SRC-002
In the server's implementation (`bin/agr-chat.js:13`): 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: import { spawn } from 'child_process'; import path from 'path'; import { fileURLToPath } from 'url'; const __filename
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 bin/agr-chat.js
high Shell/command execution in server code (bin/alliance.js)MTC-SRC-002
In the server's implementation (`bin/alliance.js:11`): 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: import { spawn } from 'child_process'; import { join, dirname } from 'path'; import { fileURLToPath } from 'url'; cons
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 bin/alliance.js
high Shell/command execution in server code (src/agr-server-simple-natural-wrapper.cjs)MTC-SRC-002
In the server's implementation (`src/agr-server-simple-natural-wrapper.cjs:20`): 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: st { spawn } = require('child_process'); const path = require('path'); // The actual ESM server is in the same dire
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 src/agr-server-simple-natural-wrapper.cjs
high Shell/command execution in server code (src/agr-server-simple-wrapper.cjs)MTC-SRC-002
In the server's implementation (`src/agr-server-simple-wrapper.cjs:20`): 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: st { spawn } = require('child_process'); const path = require('path'); // The actual ESM server is in the same dire
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 src/agr-server-simple-wrapper.cjs
medium Hardcoded egress to an external endpoint (src/scientific/gene-expression.js)MTC-SRC-003
In the server's implementation (`src/scientific/gene-expression.js:157`): 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 response = await axios.get( 'https://gtexportal.org/rest/v1/expression/medianGeneExpression',
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 src/scientific/gene-expression.js
medium Hardcoded egress to an external endpoint (src/scientific/protein-structure.js)MTC-SRC-003
In the server's implementation (`src/scientific/protein-structure.js:163`): 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 response = await axios.get( `https://www.ebi.ac.uk/pdbe/api/mappings/uniprot/${uniprotId}`, { tim
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/scientific/protein-structure.js
medium Hardcoded egress to an external endpoint (src/scientific/variant-analysis.js)MTC-SRC-003
In the server's implementation (`src/scientific/variant-analysis.js:317`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await axios.post( 'https://rest.ensembl.org/vep/human/hgvs', { hgvs_notations: [varian
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/scientific/variant-analysis.js
low Hardcoded egress to an external endpoint in packaging/dev tooling (scripts/benchmark.js)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/benchmark.js:231`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { await axios.get('https://www.alliancegenome.org/api/search', { params: { q: `test_${i}`, lim
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 scripts/benchmark.js
low Shell/command execution in packaging/dev tooling (scripts/easy-query.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/easy-query.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: import { spawn } from 'child_process'; // Simple query functions const queries = { genes: (query, limit = 5) => ({
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 scripts/easy-query.js
low Shell/command execution in packaging/dev tooling (scripts/query-helper.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/query-helper.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: import { spawn } from 'child_process'; import { createInterface } from 'readline'; class AGRQueryHelper { constructo
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 scripts/query-helper.js
low Shell/command execution in packaging/dev tooling (scripts/test-mcp-setup.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/test-mcp-setup.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: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import { dirname, join } from 'path'; impor
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 scripts/test-mcp-setup.js
Tools 28
Each tool and what it can reach — statically extracted from the published source.
analyze_research_trendsno sensitive capabilityanalyze_variantno sensitive capabilityaskno sensitive capabilityblast_sequenceno sensitive capabilitybuild_phylogenetic_treeno sensitive capabilityclear_cacheno sensitive capabilitycomplex_searchno sensitive capabilitycontinue_conversationno sensitive capabilityexplain_understandingno sensitive capabilityfaceted_searchno sensitive capability
Show 18 more tools ↓
find_gene_relationshipsno sensitive capabilityfind_orthologsno sensitive capabilityfunctional_enrichment_analysisno sensitive capabilityget_cache_statsno sensitive capabilityget_conservation_scoreno sensitive capabilityget_drug_interactionsno sensitive capabilityget_expression_heatmapno sensitive capabilityget_gene_diseasesno sensitive capabilityget_gene_expressionno sensitive capabilityget_gene_infono sensitive capabilityget_gene_pathwaysno sensitive capabilityget_protein_structureno sensitive capabilityget_species_listno sensitive capabilitypathway_enrichmentno sensitive capabilityprocess_natural_queryno sensitive capabilitysearch_diseasesno sensitive capabilitysearch_genesno sensitive capabilitysearch_literatureno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (28 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 |
|---|---|---|---|---|
v3.2.6 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 agr-mcp-server-enhanced --onlineMore in Learning & Documentation
stdio compatibility bridge for the hosted AgentMail MCP server
MCP server for Alfa documentation retrieval
MCP server providing Alpine.js documentation and reference
Search the official Astro framework documentation.
MCP server providing ATAG 2.0 (Authoring Tool Accessibility Guidelines) guidance for authoring tool developers
Aurais Research Reader as an MCP server — paste a paper or article, get a structured read with verbatim-verified quotes + a signed Vorion proof chain (via @vorionsys/aurais-core).