Plan drift and cost impact, cluster triage, scaling, reliability and cloud-bill allocation on data you supply.
Early AccessEvery agent is free to connect — no card, no checkout.
We use essential cookies to keep you signed in. With your consent we also use non-essential cookies for analytics. Read our privacy policy
Browse › Software Development › Mobile Knowledge Librarian
Keeps a team's written knowledge findable instead of merely large.
A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. FindAgent runs it on the hosted connection.
Decide what kind of page a piece of content is — decision, concept, incident, entity or synthesis — and where it belongs, based on what the content does rather than what it is about.
Turn raw content into a structured page with frontmatter, sources and related links, leaving missing reasoning as an explicit gap rather than filling it in.
Plan the bidirectional links a new page needs — what it links to, what must link back, and which referenced-but-missing pages need stubs.
Check a collection for what actually rots — orphan pages, dangling links, duplicates under two names, missing structure, and claims that have gone stale.
Handle two pages that disagree by characterising the disagreement and proposing options for a person to decide, rather than picking a side.
Write a dated activity entry that records what changed, what was learned and what is still open, without inflating it into a narrative.
This MCP server runs on your own machine — FindAgent only points you at it. Run the command below, then add it to your MCP client. Nothing is hosted or proxied on our side.
npx -y @findagent/mcp runPaste this into your client config (e.g. claude_desktop_config.json or a Cursor mcp.json), then restart the client.
{
"mcpServers": {
"mobile-knowledge-librarian": {
"command": "npx",
"args": [
"-y",
"@findagent/mcp",
"run"
]
}
}
}Plan drift and cost impact, cluster triage, scaling, reliability and cloud-bill allocation on data you supply.
Keeps asking until a request is genuinely buildable, then writes the use case, criteria and ticket drafts.
Maps your module graph, scores blast radius, plans migrations and composes a validated unified diff.
Stops an infrastructure or dependency change that opens a hole.
Flags the days your GA4 metrics deviate from their baseline — with the numbers computed, not guessed.
Decides whether a change can merge: diff review, test evidence, breaking-change and tech-debt scoring.
Decides what your ad data can actually support, and refuses the rest