claude-context-local
Provides Claude Code with local semantic search and indexing of your codebase using AST-aware chunking and hybrid search, enabling deep code understanding without sending data to the cloud.
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
tazhate
Source: Glama
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.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
index_projectIndex or re-index a project for semantic code search.
search_codeSearch code using hybrid semantic + keyword (BM25) search.
search_allSearch across ALL indexed projects at once.
search_diffSearch only code that changed since a git ref (commit, branch, tag).
find_symbolFind who calls a function/method, or what it calls (symbol dependency graph).
index_statusCheck the indexing status of a project.
drop_indexRemove the index for a project.
CCL_MODELall-MiniLM-L6-v2 Embedding model (default uses built-in ONNX, no PyTorch)CCL_CHUNK_LINES50 Max lines per chunkCCL_CHUNK_OVERLAP10 Overlap lines between chunksCCL_DATA_DIR~/.cache/claude-context-local Index storage directoryCCL_HYBRID_ALPHA0.7 Search blend: 0=BM25 only, 1=semantic onlyCCL_CONTEXT_LINES5 Default surrounding context lines in resultsTool 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
7/7 tools missing one or more hints — index_project (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_code (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_all (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +4 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.
Destructive tools are labelled
1 tool perform destructive updates without destructiveHint — drop_index deletes at line 1762 (shutil.rmtree(db_path))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Tool handlers catch errors
5/7 tool handlers wrap calls in try/catch (71%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
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/tazhate/claude-context-local)?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