agentsearch-mcp
A remote MCP connector that exposes AgentSearch API endpoints as discoverable, typed MCP tools for LLM agents. It provides web search, instant answers, and URL-to-text fetching capabilities, acting as a thin adapter layer for MCP clients like Claude and ChatGPT without adding business logic.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://agentsearch-mcp.vercel.app/mcpWhat its tools do
3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Read-only (3)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Perform web SERP searches via provider-abstracted backends
- Retrieve keyless DuckDuckGo instant answers for definitions and facts
- Fetch and clean text or markdown from URLs for LLM context windows
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- agentsearch 1.0.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 3 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": true
}
}Tools
3 advertised
web_search — Web search (SERP)
Search the web via a provider-abstracted backend (Brave or Serper, configured operator-side). Returns normalized results, each with position, title, url, snippet, source, and domain, plus a meta envelope (cache state, provider, took_ms). Returns a provider_required error if no search provider key is configured upstream. Use this for a full web SERP; use instant_answer for quick facts/definitions.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"description": "Search query."
},
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Max results, clamped to 1-20. Default 10."
},
"country": {
"type": "string",
"description": "ISO-3166 alpha-2 region, lowercase. Default us."
},
"provider": {
"enum": [
"brave",
"serper"
],
"type": "string",
"description": "Force a specific provider. Omit to use whichever is configured operator-side."
}
}
}{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}instant_answer — Instant answer (keyless)
DuckDuckGo Instant Answer API — definitions, entities, and quick facts. Returns a normalized answer with heading, type (abstract/answer/disambiguation), source, sourceUrl, optional image/definition, and relatedTopics, plus a meta envelope. Not a full web SERP; use web_search for that. Works with no API key.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"description": "Query."
}
}
}{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}fetch_url — Fetch a URL as clean text/markdown (RAG-ready)
Fetches any public http(s) URL, strips boilerplate (scripts, nav, footer, ads), and returns clean text or markdown ready for an LLM context window. SSRF-guarded — refuses private/loopback/internal hosts. Returns url, title, format, length, content (and finalUrl when redirected, plus up to 50 extracted links when links=true), with a meta envelope. Works with no API key.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The URL to fetch (public http/https only)."
},
"links": {
"type": "boolean",
"description": "Also return up to 50 extracted links. Default false."
},
"format": {
"enum": [
"text",
"markdown"
],
"type": "string",
"description": "Output format. Default text."
},
"maxChars": {
"type": "integer",
"maximum": 500000,
"minimum": 500,
"description": "Max characters of content returned, clamped 500-500000. Default 100000."
}
}
}{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}Prompts
Not advertised
Resources
Not advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-06: 1 of 1 checks answered
- 2026-11-07: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 448 ms
- 95th percentile latency
- 448 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 448 ms · metadata changed · 3 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http agentsearch-mcp-vercel https://agentsearch-mcp.vercel.app/mcpCodex
codex mcp add agentsearch-mcp-vercel --url https://agentsearch-mcp.vercel.app/mcpCursor
{
"mcpServers": {
"agentsearch-mcp-vercel": {
"url": "https://agentsearch-mcp.vercel.app/mcp"
}
}
}Cline
{
"mcpServers": {
"agentsearch-mcp-vercel": {
"type": "streamableHttp",
"url": "https://agentsearch-mcp.vercel.app/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"agentsearch-mcp-vercel": {
"type": "http",
"url": "https://agentsearch-mcp.vercel.app/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http agentsearch-mcp-vercel https://agentsearch-mcp.vercel.app/mcpClaude Desktop
https://agentsearch-mcp.vercel.app/mcpWindsurf
{
"mcpServers": {
"agentsearch-mcp-vercel": {
"serverUrl": "https://agentsearch-mcp.vercel.app/mcp"
}
}
}Let your agent find its tools
Find servers like agentsearch-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.