slopweaver
Searches open pull requests, mentions, and recent repository activity to identify work items.
Searches emails to identify pending communications. (Planned for v1.1+)
Searches calendar events to identify upcoming commitments. (Planned for v1.1+)
Searches tickets and issues to identify priority work items. (Planned for v1.1+)
Searches mentions, threads awaiting reply, and messages to identify action items.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@slopweaverwhat should I work on next?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Slopweaver
A local-first, zero-key org world model — the own-your-data alternative to hosted enterprise search.
Point Slopweaver at a GitHub repo and it builds a queryable world model of your team's work, entirely on your machine: it ingests the history, runs a tiered bronze → silver → gold synthesis, and lets you ask grounded, cited questions of it. No API keys, no data leaving your machine, no accounts.
/slopweaver:onboard your-org/your-repo
/slopweaver:ask "what has the team shipped recently, and what's blocked?"Why
Zero-key. Nothing to configure. Language-model calls run on your existing Claude Code session (via the
claudeCLI — no API key, no SDK). Embeddings run on-device. The only optional credential is a GitHub token for private repos, and it defaults to yourghCLI login.Local-first. Your world model lives under
$SLOPWEAVER_HOMEon your machine. The only things that leave it are the GitHub reads you authorise and the Claude calls you already make. See docs/security.md.Runs anywhere. No native build step — inference is pure WASM. The same plugin works on macOS, Linux, and Windows, on any CPU architecture.
Grounded, not hallucinated. Every answer cites the exact records it's built from; a citation the model can't back is stripped, not shown.
Related MCP server: code-context
Install (as a Claude Code plugin)
/plugin marketplace add /path/to/slopweaver
/plugin install slopweaver@slopweaver-devOn first session the plugin installs its own dependencies into its plugin-data dir (one-time, ~a
minute) — you don't run npm install. Requires Node + Corepack/Yarn and the claude CLI (you already
have it). Then run /slopweaver:onboard to build your first world model.
The pipeline
Command | Stage | What it does |
| bronze | Ingest recent GitHub activity (PRs, issues, reviews, comments) into a local corpus. Incremental — resumes from a watermark. |
| silver | Free, deterministic synthesis: a people/container directory, a cross-ref graph, and opportunity detection. |
| gold | LLM map-reduce into grounded markdown digests (via your Claude session; caches per batch, so re-runs are cheap). |
| query | A grounded, cited answer over hybrid retrieval (on-device semantic ⊕ keyword, fail-soft to keyword). |
| query | The raw ranked record slice, no LLM — for feeding a subagent or eyeballing the corpus. |
To update: re-run refresh → derive → distil. refresh pulls only new activity; distil only
re-synthesises batches whose content changed.
Trust
The biggest objection to any tool that ingests company data is "where does it go?" — here, nowhere you don't already send it. A shipped hygiene gate scans every tracked file for leak classes (secrets, absolute paths, raw workspace IDs) and runs in CI + a local pre-push hook, so neither you nor a fork can commit your org's secrets. Full threat model + data-flow: docs/security.md.
Development
Requires Node (see .nvmrc) and Yarn 4 (via Corepack —
corepack enable once).
yarn install
yarn slopweaver doctor # smoke-test the CLI
yarn typecheck # tsc --noEmit
yarn test:unit # vitest
yarn hygiene # public leak-class gateArchitecture: docs/architecture.md.
License
MIT — see LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/slopweaver/slopweaver'
If you have feedback or need assistance with the MCP directory API, please join our Discord server