CodebaxingSAFE
Local codebase indexing and semantic code search via MCP
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/codebaxing) [](https://opensource.org/licenses/MIT)
English | Tiếng Việt
MCP server for semantic code search. Index your codebase once, then search using natural language.
How It Works
Your Code → Tree-sitter Parser → Symbols → Embedding Model → Vectors → ChromaDB ↓ "find auth logic" → Embedding → Query Vector → Similarity Search → Results
Traditional search matches exact text. Codebaxing understands meaning:
Quick Start
1. Start ChromaDB
docker run -d -p 8000:8000 --name chromadb chromadb/chroma
2. Index Your Codebase (CLI)
npx codebaxing@latest index /path/to/your/project
This creates a .codebaxing/ folder with the index. Only needs to be done once per project.
Performance note: Local embedding is slow (~4 min for ~4,000 files). For faster indexing, use Gemini embedding (free) — see Cloud Embedding below.
3. Install MCP Server for AI Editors
npx codebaxing install # Claude Desktop npx codebaxing install --cursor # Cursor npx codebaxing install --windsurf # Windsurf npx codebaxing install --all # All editors
Restart your editor. Now you can ask: "Find the authentication logic"
CLI Commands
a6e63d2870feOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add codebaxing --env CODEBAXING_GEMINI_API_KEY=${CODEBAXING_GEMINI_API_KEY} --env CODEBAXING_OPENAI_API_KEY=${CODEBAXING_OPENAI_API_KEY} --env CODEBAXING_VOYAGE_API_KEY=${CODEBAXING_VOYAGE_API_KEY} --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"codebaxing": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CODEBAXING_GEMINI_API_KEY": "${CODEBAXING_GEMINI_API_KEY}",
"CODEBAXING_OPENAI_API_KEY": "${CODEBAXING_OPENAI_API_KEY}",
"CODEBAXING_VOYAGE_API_KEY": "${CODEBAXING_VOYAGE_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}Exposed tools (9)
8 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
clean | read | Clean all indexed data for a codebase. Deletes ChromaDB collection and .codebaxing/ data. Preserves user config (ignore.json). Use this to fix corrupted indexes or start fresh. |
forget | destructive | DESTRUCTIVE: Remove memories matching specified criteria. Delete by: memory_id, memory_type, tags, older_than (1d, 7d, 30d, 1y) |
index | read | Index a codebase for semantic search. REQUIRED FIRST STEP. Modes: - auto (default): Smart detection. If index exists, updates incrementally. - full: Force complete re-index. - load-only: Just load existing index without any indexing. Creates a .codebaxing/ folder in the codebase directory. |
languages | read | List all supported programming languages and file extensions. |
memory-stats | read | Get statistics about stored memories for the current project. |
recall | read | Retrieve memories using semantic search. Filters: memory_type, tags, time_range (today, week, month, all) |
remember | read | Store a memory for later retrieval. Memory types: conversation, status, decision, preference, doc, note TTL options: session (24h), day, week, month, permanent (default) |
search | read | Semantic search for code. Returns ranked code chunks with file paths and line numbers. Examples: - search(question= |
stats | read | Get statistics about the currently loaded codebase index. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (7)
forget
path.join(__dirname, '../../node_modules/tsx/dist/esm/index.mjs'),
path.join(__dirname, '../../../node_modules/tsx/dist/esm/index.mjs'),
} from '../../src/core/exceptions.js';
} from '../../src/core/models.js';
} from '../../src/parsers/language-configs.js';
@huggingface/transformers, @modelcontextprotocol/sdk, chromadb, tree-sitter, tree-sitter-bash, tree-sitter-c, tree-sitter-c-sharp, tree-sitter-cpp
Gates applied: no_behavioural_pass.
a6e63d2870fefull audit observations/trust-audit/mcp-server/duysolo__codebaxing.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | a6e63d2870fe | SAFE | B | 89 | first audit |
Questions
What is the Codebaxing MCP server?
Local codebase indexing and semantic code search via MCP
What tools does Codebaxing expose?
9 in total: 8 read-only, 0 that write, and 1 that can delete or overwrite (forget). Every one is listed on this page with its risk.
Is Codebaxing safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Codebaxing need?
It reads CODEBAXING_GEMINI_API_KEY, CODEBAXING_OPENAI_API_KEY, CODEBAXING_VOYAGE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY and VOYAGE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Codebaxing run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as codebaxing at 1.0.5.
How current is this page?
The grade is for one exact copy of the source (a6e63d2870fe), read on 2026-10-08. The repository is watched and re-audited when it changes.