brave-answers-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BRAVE_ANSWERS_KEY | Yes | API key for Brave Answers API. Must be kept secret. |
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 |
|---|---|
| answersA | Brave Answers: AI-synthesized, web-grounded answer with source citations. One blocking call, |
| research_submitA | Submit a Brave Answers RESEARCH job: multi-iteration web research (~90-300s). Cost ≈ $0.07 × queries actually run (narrow ≈ $0.07, broad ≈ $0.77, full 20-query runs can exceed $1) — only use when the user explicitly requests deep research. Returns a research_id immediately; the job runs in the background. Poll with research_status and fetch the deliverable with research_result once completed. |
| research_statusA | Check the status of a submitted Brave Answers research job (research_id from research_submit). Returns running/completed/failed, elapsed time, and latest progress. |
| research_resultA | Fetch the result of a completed Brave Answers research job (research_id). If the job is still running, this returns how long it has been running — call again later. |
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 4 tools
The tool set cleanly separates a single-shot direct answer from the multi-step research job lifecycle. The research_submit/status/result trio has clear sequential roles with no overlap, and descriptions reinforce when each should be used.
The research_* prefix creates a clear and consistent pattern for the job lifecycle, while 'answers' stands alone as the direct-answer tool. Though not perfectly uniform, the naming is predictable and readable.
With 4 tools, the server is well-scoped for its purpose: one for quick answers, three for asynchronous research jobs. Each tool has a distinct role with no redundancy.
The research lifecycle is fully covered with submit, status, and result. The only minor gap is the lack of explicit cancellation or listing of historical jobs, but these are not essential for the server's stated purpose.