klawsearch-mcp
MCP server for KlawSearch — gives MCP-compatible agents (Claude Desktop, Goose, Cursor, OpenClaw) a search tool that returns clean, ranked, agent-ready results instead of raw links.
pip install klawsearch-mcp
Get a free API key at klawsearch.com (1,000 requests/month, no card required).
Tools exposed
| Tool | What it does |
|---|---|
klawsearch_search |
Ranked results + an optional synthesized, source-cited answer |
klawsearch_extract |
Fetch a URL and return cleaned, LLM-ready text |
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"klawsearch": {
"command": "klawsearch-mcp",
"env": { "KLAWSEARCH_API_KEY": "ks-live-..." }
}
}
}
Goose
~/.config/goose/config.yaml:
extensions:
klawsearch:
type: stdio
cmd: klawsearch-mcp
envs:
KLAWSEARCH_API_KEY: ks-live-...
Configuration
| Env var | Required | Default |
|---|---|---|
KLAWSEARCH_API_KEY |
yes | — |
KLAWSEARCH_BASE_URL |
no | https://api.klawsearch.com |
Point KLAWSEARCH_BASE_URL at your own instance if you self-host KlawSearch.
Why KlawSearch
Built for agents rather than people: hybrid retrieval (BM25 + vector + RRF), grounded answers with citations, SEC/EDGAR financial filings the general-purpose search APIs don't index, and a stack you can self-host.
- Website: https://klawsearch.com
- Python SDK:
klawsearch
MIT licensed.
1 maintainer
Metadata
1 maintainer
Release files for klawsearch-mcp 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| klawsearch_mcp-0.1.0.tar.gz | 4.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| klawsearch_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 9.0 kB
Release files / klawsearch_mcp-0.1.0.tar.gz
| Download URL | klawsearch_mcp-0.1.0.tar.gz |
|---|---|
| Size | 4.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e5a99b3aa7122e68980bd88d5ab5377578b6f77a5f48dd72a879c3f35e170420
|
|
BLAKE2b-256 checksum How to use checksums |
386a9f161ba7840255cc6f888a99bfc8702d554a63ef200066bc55388e3e39aa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.9
|
Release files / klawsearch_mcp-0.1.0-py3-none-any.whl
| Download URL | klawsearch_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
243b4d076e0396f05c595071d5ffd574b54ab0da2e3d7cfb243a9a6490758057
|
|
BLAKE2b-256 checksum How to use checksums |
18a846bd4b0a6499b3e943f88bf212426babf18fd2dddc04c272261adf7443e3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.9
|
