BRAINS MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VOYAGE_API_KEY | Yes | Voyage API key for embeddings | |
| ANTHROPIC_API_KEY | Yes | Anthropic API key for Claude |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| lookup_leadA | Look up a lead by email address, with their company's firmographics. This is the entry point for qualifying any lead. Call this first — the other tools take their arguments from what this returns. |
| check_crmA | Look up a company's CRM history: its deals and support tickets. |
| score_leadA | Score a lead 0-100 against deterministic qualification rules. Scoring is rule-based, not model-based: the same lead always produces the same score, and every point is explained in "reasons". |
| search_knowledgeA | Search the internal knowledge base for playbook and policy context. |
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
Each tool has a clearly distinct job: lookup_lead retrieves firmographic basics, check_crm pulls deal/ticket history, score_lead applies rules, and search_knowledge provides policy context. No two tools are interchangeable.
All tool names follow the same lowercase verb_noun pattern: lookup_lead, check_crm, score_lead, search_knowledge. The convention is consistent and makes each tool's purpose predictable.
Four tools is a tightly scoped set for a lead qualification workflow. Each tool maps to one necessary stage, with no redundant or decorative additions.
The toolset covers the full qualification lifecycle: find the lead, inspect CRM history, score the lead, and consult internal knowledge. While it does not offer write operations, the stated purpose is read-oriented qualification, so the surface is coherent and complete for that workflow.