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.
npx agentmods add mcp/riemannulus/knowledge-base/kb-workflow-kbgit clone --depth 1 https://github.com/riemannulus/knowledge-baseGrade A, and why
kb 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 2d 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
{
"kb": {
"type": "http",
"url": "${user_config.kb_mcp_url}",
"headers": {
"Authorization": "Bearer ${user_config.kb_auth_token}"
}
}
}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.
- 2d ago First seen · 9 lines scan A 63a94f6ab005
kb is an MCP server published in the GitHub repository riemannulus/knowledge-base (1 stars, last pushed 21d ago), licensed MIT. 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
fortemi
MCP server "fortemi" as configured in Fortemi/fortemi. Runs ./mcp-server/index.js with node. Needs 2 environment variables to run.
kbdb
A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown. Runs locally from the @dikolab/kbdb npm package.
markdown-vault-mcp
Generic markdown vault MCP with hybrid search. Runs locally from the markdown-vault-mcp Python package. Needs 81 environment variables to run.
connapse
MCP server "connapse" as configured in Destrayon/Connapse. Runs in Docker (ghcr.io/destrayon/connapse:v0.3.2).
re-call
Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention. Runs locally from the recall-rag Python package. Needs 3 environment variables to run.
mcp-server
Typed record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer. Runs locally from the @vectros-ai/mcp-server npm package. Needs 3 environment variables to run.