Agr Mcp Server Enhanced MCP Server
agr-mcp-server-enhanced
npm
v3.2.6
Published by nuin — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.
Started at 100 and nothing was deducted: the deterministic scan raised no scored threat in the published surface it inspected. Capability observations and advisory notes are recorded but never lower the score.
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: 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 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: 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 bin/alliance.js
high Shell/command execution in server code (scripts/easy-query.js)MTC-SRC-002
In the server's implementation (`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: 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 scripts/easy-query.js
high Shell/command execution in server code (scripts/query-helper.js)MTC-SRC-002
In the server's implementation (`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: 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 scripts/query-helper.js
high Shell/command execution in server code (scripts/test-mcp-setup.js)MTC-SRC-002
In the server's implementation (`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: 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 scripts/test-mcp-setup.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: 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 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: 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 src/agr-server-simple-wrapper.cjs
medium Hardcoded egress to an external endpoint (scripts/benchmark.js)MTC-SRC-003
In the server's implementation (`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: axios.get('https://www.alliancegenome.org/api/search'
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
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: 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: axios.get(
`https://www.ebi.ac.uk/pdbe/api/mappings/uniprot/${uniprotId}`
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: axios.post(
'https://rest.ensembl.org/vep/human/hgvs'
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
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
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 100/100 | 11 | 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.
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
Security scan results for the Ab Integrations MCP server.
Security scan results for the Academic Research MCP server.
Security scan results for the Academic Research Mcp Suite MCP server.
Security scan results for the Adonis Docs MCP server.
Security scan results for the Adonis Mcp Docs MCP server.
Security scan results for the Advisor MCP server.