AgentSearch MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTSEARCH_MODE | No | The mode to run the server in: 'direct' (local/self-hosted AgentSearch) or 'portal' (Pocket Network agent portal). Defaults to 'direct'. | direct |
| AGENTSEARCH_API_KEY | No | Optional API key for direct mode. Sent as `Authorization: Bearer …`. On 401, the client retries once without the key. | |
| AGENTSEARCH_BASE_URL | No | Base URL for the direct-mode AgentSearch backend (no trailing slash). Defaults to http://127.0.0.1:8000. | http://127.0.0.1:8000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| agentsearch_web_searchA | Search the web via AgentSearch. Uses AGENTSEARCH_MODE=direct (local API) or portal (Pocket). Returns structured JSON results. |
| agentsearch_extractA | Extract page content from a URL via AgentSearch POST /v1/extract (direct mode only). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one performs web searches, the other extracts page content from a given URL. There is no ambiguity about which tool to use for a given task.
Both tools share the 'agentsearch_' prefix and use snake_case, but 'web_search' follows a verb_noun pattern while 'extract' is a bare verb. This is a minor inconsistency that does not cause confusion.
With only two tools, the server feels thin for a typical MCP service, but the scope is narrow—web search and extraction—so the count is borderline rather than inappropriate. It sits just below the typical 3-15 tool range.
The tool surface covers the two core operations of the domain: searching the web and extracting content from a result URL. There are no obvious dead ends or missing operations given the stated purpose.