codeatlas-mcp-server@1.5.9
VERIFIED· not startedPublisher claims: "Local-first MCP server for CodeAtlas — AST analysis, codebase intelligence, semantic memory, and A2A orchestration." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
ANTHROPIC_API_KEYCODEATLAS_API_KEYGEMINI_API_KEYOPENCODE_API_KEYConfiguration, not credentials: CLAUDE_CODE_ENTRYPOINT, CLAUDE_PROJECT_DIR, CLAUDECODE, CODEATLAS_ALLOW_CUSTOM_URL, CODEATLAS_API_TIMEOUT_MS, CODEATLAS_API_URL, CODEATLAS_CLAUDE_PROJECTS_DIR, CODEATLAS_CLI_PATH, CODEATLAS_CONTEXT_CACHE_DIR, CODEATLAS_CONTEXT_MAX_CHARS, CODEATLAS_CONTEXT_SUPPRESS_DUPLICATES, CODEATLAS_DURABLE_CAPTURE, CODEATLAS_HOOK_TOOLS_ALLOWLIST, CODEATLAS_HOOK_TOOLS_DENYLIST, CODEATLAS_INJECT_BRAIN_CONTEXT, CODEATLAS_MEMORY_SPOOL_DIR, CODEATLAS_MIN_QUERY_WORD_LENGTH, CODEATLAS_MIN_RELEVANCE_SCORE, CODEATLAS_MULTI_TENANT, CODEATLAS_PROJECT, CODEATLAS_PROJECT_DIR, CODEATLAS_PROJECT_DIRS, CODEATLAS_PROJECT_ID, CODEATLAS_PROJECTS_ROOT, CODEATLAS_SCAN_AI_KEY, CODEATLAS_SCAN_AI_MODEL, CODEATLAS_SCAN_AI_URL, CODEX_HOME, GEMINI_CLI_IDE_WORKSPACE_PATH, OPENCODE_BASE_URL, PATHEXT, SKILL_MD_PATH- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard. It asks for ANTHROPIC_API_KEY, CODEATLAS_API_KEY, GEMINI_API_KEY, OPENCODE_API_KEY and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 10 s · 2 scenarios · 0 deviationsStatic findings
const foundKey = parsed.mcpServers[serverName]?.env?.CODEATLAS_API_KEY;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const globalEnvPath = path.join(os.homedir(), ".codeatlas", ".env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.claude mcp add codeatlas -- npx -y @giauphan/codeatlas-mcpFix: Pin versions and sources; vendor anything fetched at install time.ignoredDirectoryNames.has(component)) || basename === '.env' || basename.endsWith('.log') || basename.endsWith('.pyc');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.claude mcp add codeatlas -- npx -y @giauphan/codeatlas-mcpFix: Pin versions and sources; vendor anything fetched at install time.…", "listagents", "taskoutput"]); const SENSITIVE_SOURCE = /(?:^|[\s"'=:/\\])(?:\.env(?:\.[A-Za-z0-9_-]+)?|\.npmrc|\.pypirc|\.ssh|id_(?:rsa|ed25519)|authorized_keys|…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if (parsed.mcpServers?.codeatlas?.env?.CODEATLAS_API_KEY) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if (existing.mcpServers?.["codeatlas-genome"]?.env?.CODEATLAS_API_KEY) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// ⚠️ NOTE: API key must be set via CODEATLAS_API_KEY environment variable or .env file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(` • PostToolUse / PostToolUseFailure / Stop / PreCompact: native brain-save`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.# Run chmod +x after editing, then restart Claude server.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.…['node_modules', 'dist', 'out', '.git', '__pycache__', '.venv', 'venv', 'env', '.env', 'vendor', 'build', '.tox', '.mypy_cache', '.pytest_cache', 'coverage', '.next…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// Save the key securely to ~/.codeatlas/.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if (existing.mcpServers?.codeatlas?.env?.CODEATLAS_API_KEY) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for codeatlas-mcp-server@1.5.9 as of 16 h ago. This is the package itself, not its dependencies.