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/AgentsKit-io/doc-bridgeWrote 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/agentskit-io/doc-bridge/ak-docs)<a href="https://agentmods.dev/mcp/agentskit-io/doc-bridge/ak-docs"><img src="https://agentmods.dev/badge/mcp/agentskit-io/doc-bridge/ak-docs/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/agentskit-io/doc-bridge/ak-docs"><img src="https://agentmods.dev/badge/mcp/agentskit-io/doc-bridge/ak-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ak-docs 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 yesterday.
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
{
"ak-docs": {
"command": "npx",
"args": [
"-y",
"@agentskit/[email protected]",
"mcp"
]
}
}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.
- yesterday Changed 81ed7a78a3ba
- 4d ago Changed 726227afed94
- 5d ago Changed 20318fe932e7
- 7d ago Changed 6b96a0735406
- 8d ago Changed 095efc7faa19
- 9d ago Changed c9a4521af8a1
- 14d ago Changed 1b32a105b031
- 20d ago Changed 7088c9b358e8
- 27d ago Changed 502c324d55cf
- 29d ago First seen · 10 lines scan A 0cd94a987704
ak-docs is an MCP server published in the GitHub repository AgentsKit-io/doc-bridge (10 stars, last pushed yesterday), 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
doc-manager
MCP server for comprehensive documentation lifecycle management. Runs locally from the doc-manager-mcp Python package.
geml
Read and edit long Markdown by block instead of by file — geml list/find/get address any .md, nothing is converted. Plus GEML, a plain-text format where blocks carry ids for validated writes, reference checks and per-block history. Ships an MCP server. Runs locally from the @geml/geml npm package.
markdown
Markdown MCP — search, extract sections, list headings, find code blocks. Runs locally from the mcp-server-markdown npm package.
fonto-docs
Fonto (FontoXML) documentation for AI tools. Converts DITA XML to Markdown on demand. Remote server at fonto-docs.elliat.nl.
jdocmunch-mcp
Token-efficient MCP server for structured documentation retrieval via section-level indexing. Runs locally from the jdocmunch-mcp Python package.
vobiz-docs
MCP server "vobiz-docs", hosted remotely at vobiz.ai, as configured in vobiz-ai/Agent-Skills.