Scout
Optionally uses a Brave API key to discover new domains for crawl intents when local search coverage is thin, helping Scout grow its corpus beyond existing pages.
Optionally connects to a local Ollama instance to generate embeddings and enable vector/hybrid search alongside BM25; without it, search is lexical-only.
Supports bootstrapping a local search corpus from a Wikipedia dump as a real-world corpus source.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Scout
A private search engine your coding agent calls over MCP.
Localhost only · five tools · no API key · the read path never touches the network.
Status: v1.3, works end to end. Python 3.12, SQLite + faiss. One loopback service, one thin stdio proxy per agent session.

A 52-document RFC corpus. That is the tool call, the JSON it returns, and the answer — nothing left the machine.
What it does
search— hybrid BM25 + vector search, 8 results inside 1,200 tokens by defaultexpand— the whole stored chunk behind one resultfetch— one page's text by URLcorpus_stats,job_status— what you have, what is runningHonest coverage — every answer carries
thin, agap(entity:duckdb) and arecommend, so the agent is told when Scout does not knowGrows on its own — thin queries become crawl intents; a Brave key is optional and only ever finds new domains
Related MCP server: localgate
Install
Needs macOS or Linux, Python 3.12 and uv. Ollama is optional — without it, search is lexical only.
git clone https://github.com/paradise-runner/scout.git
cd scout
./scripts/bootstrap.sh # .venv from requirements.lock, ~25 sFirst run
# 1. A corpus. 50 RFCs, one to two minutes of polite fetching.
PYTHONPATH=.:src .venv/bin/python -m bootstrap rfc --db scout.db --from 9110 --limit 50
# 2. The service.
./src/api/scout serve --db scout.db &
# 3. The same JSON your agent gets.
./src/api/scout search "HTTP semantics"
# 4. Register: paste the printed block into ~/.pi/agent/mcp.json, then /reload in pi.
./src/api/scout registerAsk pi: Use scout to find what RFC 9110 says about identifiers.
Use
you want | run |
service up / down |
|
is it alive |
|
add one page |
|
crawl a site |
|
a real corpus |
|
Limits (v1)
Corpus is only what you bootstrap or crawl. It is not an index of the public web.
coverage.thin: truemeans "few results, small corpus". That is the contract working, not a bug.HTML only. No PDFs, video, or code repositories.
No auth. Loopback only — do not bind
0.0.0.0.Vector search needs a local Ollama and a built index; without them you get lexical answers.
Speed. ~2–130 ms per query on the 50-RFC corpus above (
meta.took_ms, warm to cold). A 3,400-document corpus can take seconds on a cold disk; numbers are inbench/REPORT.md.No UI. The v1.1 browser page is only in git history:
git checkout 183abb5 -- src/ui.
How it runs
scout serve one process: corpus, index, HTTP on 127.0.0.1:8771
python -m src.api.mcp_proxy one per agent session: five MCP tools, no corpus openAgent sessions hold nothing but a socket, so any number of them share one warm corpus. Raw HTML is kept forever; SQLite, markdown and vectors rebuild from it offline.
Development
./scripts/test-all.sh # 12 packages, one pytest run each
./scripts/test-all.sh api # just oneEvery src/<package>/README.md documents that package: what it does, its tests, its repro command.
Docs
PROJECT_VISION.md · SPEC.md · ROADMAP.md · deploy/ · roadmap/status/
License
Apache-2.0. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Private, multimodal knowledge store for agents: hybrid search with cited, provenance-backed results.
Token-efficient search for coding agents over public and private documentation.
Your personal library, readable by AI agents: durable snapshots, hybrid search, 46 MCP tools.
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables coding agents to search a local, offline archive of past sessions and repository Markdown docs using hybrid lexical and semantic retrieval, and read matching records to ground new work in prior knowledge without external calls.2MIT
- AlicenseAqualityBmaintenanceEnables local AI agents to perform hybrid search (BM25 + vector) over privately indexed local files, including notes, PDFs, DOCX, source code, and OCR'd images. All indexing and retrieval stay on the machine with read-only, whitelist-scoped access.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to search a locally indexed codebase with hybrid dense, lexical, and symbol-graph retrieval, returning ranked passages with exact file:line-line citations plus graph context and index status. It keeps its index in sync via a file watcher and runs as a local sidecar with no hosted service to deploy.1MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to search and question a local, hybrid-indexed corpus of scattered notes, docs, and chat logs, returning section-level citations rather than whole files.-