Doc Bridge runs on your own machine — the client starts it, so there is no endpoint to ping. 8 315 installs a week from npm. Last commit 1 Nov 2026.
Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
We read the source, 20 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const result = spawnSync(cmd, [...args], { cwd, encoding: 'utf8' })
…raph.nodes) { if (node.areaId && !ids.has(node.areaId)) delete node.areaId; if (node.cluster && !ids.has(node.cluster)) delete node.cluster }
graph.truncation = { nodes: tally(allNodes.length + symbolTotal - retainedSymbols, graph.nodes.length), documents: tally(allNodes.filt…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add doc-bridge -- npx -y @agentskit/doc-bridge
{
"mcpServers": {
"doc-bridge": {
"command": "npx",
"args": [
"-y",
"@agentskit/doc-bridge"
]
}
}
}
[mcp_servers.doc-bridge]
command = "npx"
args = ["-y", "@agentskit/doc-bridge"]
{
"mcpServers": {
"doc-bridge": {
"command": "npx",
"args": [
"-y",
"@agentskit/doc-bridge"
]
}
}
}
{
"servers": {
"doc-bridge": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agentskit/doc-bridge"
]
}
}
}
Send PDFs for e-signature by email and SMS code. Check signing status. No document storage.
Offline self-checking to reduce AI-style wording in source code and documentation.
Delegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.
Multi-language code analysis for complexity, debt, hotspots, ownership, and defect prediction
Search NVIDIA CUDA documentation and code samples from AI coding agents.
Free live-app check by an AI agent. On request it fixes the code and tests the app again.
Codebase observatory with 56+ scanners for git health, architecture, and documentation.
Coding agents in one repo see each other, get warned before shared edits, and message.
Answers built from our own checks of this server.