Agent Search MCP

Purpose: Giving AI agents traceable web search without requiring search API keys or uncontrolled result volume.

Inferred · not functionally tested

Audience: AI developers building agent workflows

Inferred · not functionally tested

Functions: rag, data_extraction

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI, WEB · deployment: browser, cli, api_only, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: lennney.com · github.com. These links do not verify the individual claims.

Agent Search MCP sits in PulseGate's RAG, search & retrieval category. Inferred · not functionally tested: It focuses on giving AI agents traceable web search without requiring search API keys or uncontrolled result volume. Inferred · not functionally tested: It is built as an open-source project for AI developers building agent workflows. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: It runs on the web, the command line, and API, and it can be self-hosted.

It is developed by Lennney, and it first shipped in 2026. Development happens publicly on GitHub with 110 stars and 270 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are eight zero-key sources, chinese search, and search adapters. The interface is available in English and Chinese. Inferred · not functionally tested: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.