Cerase Search Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Cerase Search 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.
First-party web search for Cerase agents (TOOLS-2). Replaces the external kiso-search. Routed via cerase-litellm.
| Tool | LiteLLM alias | Use |
|---|---|---|
search(agent_id, query) | search (standard) | everyday "find / look up / latest on" |
deepsearch(agent_id, query) | deepsearch (advanced) | deeper multi-source research |
agent_id is bound by the gateway from the calling Agent's identity (same pattern as cerase-memory's user_id) and is injected into the LiteLLM request as metadata.cerase_agent_id so RecalcTenantUsage attributes the spend per-agent.
A search costs both:
deepsearch) via the SpendLogs stream, and
web_search_cr (20 cr) via the gateway's event_logmcp_call row (tool_name ∈ billable_search_tools).
Source of truth: control-plane/config/cerase.php → credit_pricing.
| Var | Default | Meaning |
|---|---|---|
LITELLM_BASE_URL | http://cerase-litellm:4000 | LiteLLM proxy base |
LITELLM_MASTER_KEY | — | provider key |
CERASE_SEARCH_ALIAS | search | override search alias |
CERASE_DEEPSEARCH_ALIAS | deepsearch | override deepsearch alias |
mcp-proxy --port 3000 -- python /app/server.py (FastMCP stdio → HTTP/SSE), identical to the other cerase-* MCP images. GHCR image ghcr.io/cerase-ai/cerase-search-mcp:<tag> built by .github/workflows/docker-publish.yml.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.