Manifest-driven MCP server scaffolder and runtime hub for tool integrations.
Most developer tooling work still happens through a UI a human drives. MCP MCP server moves it into the conversation instead. Manifest-driven MCP server scaffolder and runtime hub for tool integrations.
The SDK wrapper is the easy part. What makes an MCP server safe to put in front of a real internal tool — scoped auth/env, fail-soft error handling, validated manifests, a collision-safe registry, and a real test suite — is the engineering this engine is built around. That same production layer is hand-built per engagement; the factory scaffolds it, it doesn't fake it.
The server publishes 10 tools. What each one is for:
name — tool_name # REQUIREDKeep — alive for the hub session (one process per bot)Discover — ** git ls-files to enumerate tracked SKILL.md files under each scan rootValidate — ** checks required frontmatter fields (name, description)Cache — ** SHA-based cache keyed on prompt content; auto (default) skips re-run if output unchanged, force-refresh always re-runs, read-only never writesRun — ** invokes claude -p as a subprocess, streams outputRegistry — ** --write-registry persists discovered skills to registry.json; --check detects drift between filesystem and registry without writingClaim — Where it livesSDK — official mcp package, mcp.server.Serverenv_required — not enforced at scaffold levelConfiguration is passed through the environment: MY_API_KEY, FLEET_HEALTH_SERVER_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
The server ships on PyPI as jaimenbell-mcp-factory, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP's toolset — name, Keep, Discover and 7 more — is a fair guide to whether it matches your workflow. It is maintained by jaimenbell; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| name | tool_name # REQUIRED |
| Keep | alive for the hub session (one process per bot) |
| Discover | ** git ls-files to enumerate tracked SKILL.md files under each scan root |
| Validate | ** checks required frontmatter fields (name, description) |
| Cache | ** SHA-based cache keyed on prompt content; auto (default) skips re-run if output unchanged, force-refresh always re-runs, read-only never writes |
| Run | ** invokes claude -p <prompt> as a subprocess, streams output |
| Registry | ** --write-registry persists discovered skills to registry.json; --check detects drift between filesystem and registry without writing |
| Claim | Where it lives |
| SDK | official mcp package, mcp.server.Server |
| env_required | not enforced at scaffold level |
{
"mcpServers": {
"factory": {
"command": "uvx",
"args": ["jaimenbell-mcp-factory"],
"env": {
"MY_API_KEY": "your-value",
"FLEET_HEALTH_SERVER_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| MY_API_KEY | Credential the server authenticates with. | Yes |
| FLEET_HEALTH_SERVER_PATH | Filesystem location the server is allowed to use. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.