Tokenslim Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Tokenslim Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server exposing the tokenslim context-compression engine to any MCP host (Claude Code, Cursor, …). Stdio transport, built on the official Python mcp SDK (FastMCP).
| Tool | Args | Returns |
|---|---|---|
tokenslim_compress | content: str, content_type?: str | Compressed text, CCR hash, changed, and stats (orig_tokens / new_tokens / saved_tokens / ratio). |
tokenslim_retrieve | hash: str | { found, hash, content } — the original blob, or found: false if unknown to this session. |
tokenslim_stats | — | Cumulative session savings: compressions, orig_tokens, new_tokens, saved_tokens, ratio. |
content_type is an advisory hint echoed back; the core auto-detects the real type (JSON / log / code / diff / search / markdown / text) and picks a compressor.
pip install -e . # pulls the tokenslim core via gitRegister as a stdio MCP server. Example (Claude Code mcpServers):
{
"mcpServers": {
"tokenslim": { "command": "tokenslim-mcp" }
}
}or run directly: tokenslim-mcp / python -m tokenslim_mcp.
Each tokenslim_compress call wraps the blob as a one-message array, runs it through the core compress() (with min_bytes=0 so single blobs always get compressed), and returns the rewritten text plus token stats. The original is stored under its tokenslim.ccr.content_hash so tokenslim_retrieve can return it verbatim. tokenslim_stats reports the running total.
pip install -e ".[dev]"
ruff check .
python -m pytest -qTests call the tool handlers directly and exercise the FastMCP dispatch — no live MCP host or API keys required.
content_hashbut not yet a retrieve() / persistent store on main, so retrieval is backed by a per-session dict populated by tokenslim_compress. Hashes already use the core's content_hash, so this will switch to the core CCR store once merged (TODO(core-ccr) in engine.py). A hash from a previous process (or another server instance) will report found: false.
algorithms of its own.
Apache-2.0
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.