codebase-context
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
PatrickSys
Source: Glama · also listed on github_topic
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
glob CLI: Command injection via -c/--cmd executes matches with shell:true
hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard
Hono: app.mount() strips mount prefix using undecoded path, causing incorrect routing for percent-encoded paths
Hono: Cookie helper does not sanitize sameSite and priority, allowing Set-Cookie injection
CODEBASE_CONTEXT_ASCIICODEBASE_CONTEXT_CONFIG_PATH~/.codebase-context/config.json Override the server config file pathCODEBASE_CONTEXT_DEBOUNCE_MSCODEBASE_CONTEXT_DEBUGSet to 1 for verbose loggingCODEBASE_CONTEXT_HANDSHAKE_TIMEOUT_MSCODEBASE_CONTEXT_HTTPSet to 1 to start in HTTP mode (same as --http flag)CODEBASE_CONTEXT_INDEX_STATS_MAX_MBCODEBASE_CONTEXT_ONNX_THREADSCODEBASE_CONTEXT_PORT3100 HTTP server port override (same as --port; ignored in stdio mode)CODEBASE_CONTEXT_STDIO_IDLE_TIMEOUT_MSCODEBASE_CONTEXT_TS_GRAMMAR_DIRCODEBASE_ROOTBootstrap root for CLI and single-project MCP clientsEMBEDDING_MODELXenova/bge-small-en-v1.5 Local embedding model overrideEMBEDDING_PROVIDERtransformers openai (fast, cloud) or transformers (local, private)OPENAI_API_KEYRequired only if using openai providerTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
11/11 tools missing one or more hints — detect_circular_dependencies (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_codebase_health (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_codebase_metadata (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Shell command execution
1 child_process/subprocess call in production code — runs shell commands (src/cli-init.ts:268)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 2 high severity in production deps — glob@10.3.10 (high), hono@4.12.12 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/patricksys/codebase-context)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check