Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/caitao-ct/knowledge-baseInstalling this writes the configuration, not the program: `bash` has to be on your PATH already, or the server will not start.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/caitao-ct/knowledge-base/examples-knowledge)<a href="https://agentmods.dev/mcp/caitao-ct/knowledge-base/examples-knowledge"><img src="https://agentmods.dev/badge/mcp/caitao-ct/knowledge-base/examples-knowledge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/caitao-ct/knowledge-base/examples-knowledge"><img src="https://agentmods.dev/badge/mcp/caitao-ct/knowledge-base/examples-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
knowledge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"knowledge": {
"command": "bash",
"args": [
"-lc",
"cd /path/to/knowledge && ./bin/knowledge-mcp --transport stdio"
],
"env": {
"KB_DIR": "/path/to/knowledge/docs",
"CHROMA_DIR": "/path/to/knowledge/mcp-server/.chroma",
"CHROMA_COLLECTION": "knowledge",
"EMBED_MODEL": "BAAI/bge-small-zh-v1.5",
"INDEX_ON_STARTUP": "true"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 16 lines scan A 879bcc1ec15f
knowledge is an MCP server published in the GitHub repository caitao-ct/knowledge-base (2 stars, last pushed 4mo ago), licensed ISC. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
mcp-rag-bridge
MCP server "mcp-rag-bridge" as configured in zyay/mcp-rag-bridge. Runs locally from the mcp-rag-bridge Python package.
6-mcp-rag-with-langchain
MCP server "6-mcp-rag-with-langchain" as configured in CyprianFusi/MCP-rag-with-Chromadb. Runs locally from the 6-mcp-rag-with-langchain Python package.
rag-knowledge-mcp
MCP server for rag knowledge. Features semantic search, knowledge graph query, index document. From MEOK AI Labs. Runs locally from the rag-knowledge-mcp Python package.
mcp-research-assistant
MCP Server for Research Assistant with Vector Database Management. Runs locally from the mcp-research-assistant Python package.
haiku-rag
Local-first agentic RAG with citations - hybrid search, reranking and multimodal retrieval over your own documents, no database server required. Runs locally from the haiku-rag Python package.
haiku-rag
MCP server "haiku-rag" as configured in ggozad/haiku.rag. Launched with haiku-rag mcp --stdio.