Code (axme) MCP Server
@axme/code
npm
v0.6.3
Published by @axme — 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.
Persistent memory, decisions, and safety guardrails for Claude Code
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 − 9.5 = 91. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
2. Client adoption risk — 91 − 11 = 80. 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 |
|---|---|
| −10 | capability blast radius (critical) — 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 16
high Reads a sensitive credential path or dumps the environment (dist/cli.mjs)MTC-SRC-006
In the server's implementation (`dist/cli.mjs:1736`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ~/.ssh/id_*", "~/.aws/credentials", "~/.gnupg/*", ".env", "*.pem", "*.key"
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.mjs
high Reads a sensitive credential path or dumps the environment (dist/plugin/cli.mjs)MTC-SRC-006
In the server's implementation (`dist/plugin/cli.mjs:4377`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ~/.ssh/id_*", "~/.aws/credentials", "~/.gnupg/*", ".env", "*.pem", "*.key"
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/plugin/cli.mjs
high Reads a sensitive credential path or dumps the environment (dist/plugin/server.mjs)MTC-SRC-006
In the server's implementation (`dist/plugin/server.mjs:10792`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ~/.ssh/id_*", "~/.aws/credentials", "~/.gnupg/*", ".env", "*.pem", "*.key"
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/plugin/server.mjs
high Reads a sensitive credential path or dumps the environment (dist/server.js)MTC-SRC-006
In the server's implementation (`dist/server.js:1372`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ~/.ssh/id_*", "~/.aws/credentials", "~/.gnupg/*", ".env", "*.pem", "*.key"
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
high Dynamic code execution in server code (dist/plugin/cli.mjs)MTC-SRC-001
In the server's implementation (`dist/plugin/cli.mjs:33632`): 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: const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const v
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/plugin/cli.mjs
high Dynamic code execution in server code (dist/plugin/server.mjs)MTC-SRC-001
In the server's implementation (`dist/plugin/server.mjs:2944`): 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: const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const v
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/plugin/server.mjs
high Shell/command execution in server code (dist/cli.mjs)MTC-SRC-002
In the server's implementation (`dist/cli.mjs:1246`): 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: { execSync } from "node:child_process"; import { homedir } from "node:os"; import yaml from "js-yaml"; function defaultR
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.mjs
high Shell/command execution in server code (dist/plugin/cli.mjs)MTC-SRC-002
In the server's implementation (`dist/plugin/cli.mjs:3887`): 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: { execSync } from "node:child_process"; import { homedir } from "node:os"; function defaultRules() { return { git:
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/plugin/cli.mjs
high Shell/command execution in server code (dist/plugin/server.mjs)MTC-SRC-002
In the server's implementation (`dist/plugin/server.mjs:10302`): 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: { execSync } from "node:child_process"; import { homedir as homedir2 } from "node:os"; function defaultRules() { retur
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/plugin/server.mjs
high Shell/command execution in server code (dist/server.js)MTC-SRC-002
In the server's implementation (`dist/server.js:882`): 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: { execSync } from "node:child_process"; import { homedir as homedir2 } from "node:os"; import yaml2 from "js-yaml"; func
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 Hardcoded egress to an external endpoint (dist/cli.mjs)MTC-SRC-003
In the server's implementation (`dist/cli.mjs:6579`): 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 resp = await fetch(`https://api.github.com/repos/${REPO}/releases?per_page=30`, { headers: { Ac
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli.mjs
medium Hardcoded egress to an external endpoint (dist/plugin/cli.mjs)MTC-SRC-003
In the server's implementation (`dist/plugin/cli.mjs:40387`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const resp = await fetch(`https://api.github.com/repos/${REPO}/releases?per_page=30`, { headers: { Ac
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/plugin/cli.mjs
medium Hardcoded egress to an external endpoint (dist/plugin/server.mjs)MTC-SRC-003
In the server's implementation (`dist/plugin/server.mjs:37246`): 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 resp = await fetch(`https://api.github.com/repos/${REPO}/releases?per_page=30`, { headers: { Ac
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/plugin/server.mjs
medium Hardcoded egress to an external endpoint (dist/server.js)MTC-SRC-003
In the server's implementation (`dist/server.js:4513`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const resp = await fetch(`https://api.github.com/repos/${REPO}/releases?per_page=30`, { headers: { Ac
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 Untrusted input concatenated into a command sink (dist/cli.mjs)MTC-SRC-009
In the server's implementation (`dist/cli.mjs:1484`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: epo) { const result = execSync( `gh pr view ${prNumber} --repo "${repo}" --json state --jq .state`, { encoding
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.mjs
medium Untrusted input concatenated into a command sink (dist/server.js)MTC-SRC-009
In the server's implementation (`dist/server.js:1120`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: epo) { const result = execSync( `gh pr view ${prNumber} --repo "${repo}" --json state --jq .state`, { encoding
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
Tools 23
Each tool and what it can reach — statically extracted from the published source.
axme_decisionsingests untrusted inputaxme_get_memoryingests untrusted inputaxme_memoriesingests untrusted inputaxme_answer_questionno sensitive capabilityaxme_ask_questionno sensitive capabilityaxme_backlogno sensitive capabilityaxme_backlog_addno sensitive capabilityaxme_backlog_updateno sensitive capabilityaxme_begin_closeno sensitive capabilityaxme_contextno sensitive capability
Show 13 more tools ↓
axme_finalize_closeno sensitive capabilityaxme_get_decisionno sensitive capabilityaxme_list_open_questionsno sensitive capabilityaxme_oracleno sensitive capabilityaxme_safetyno sensitive capabilityaxme_save_decisionno sensitive capabilityaxme_save_memoryno sensitive capabilityaxme_save_oracleno sensitive capabilityaxme_search_kbno sensitive capabilityaxme_statusno sensitive capabilityaxme_update_safetyno sensitive capabilityaxme_worklogno sensitive capabilityaxme_workspaceno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (23 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 |
|---|---|---|---|---|
v0.6.3 latest |
B 80/100 | 16 | 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 @axme/code --onlineOther implementations of Code 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More 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