What Brandon Thinks Chat MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| build_chat_analysis_briefA | Structure a focused WhatsApp or iMessage analysis question, participant aliases, known gaps, privacy blockers, and an evidence plan without uploading a transcript. |
| score_interaction_signalsA | Calculate transparent shares and rates from user-supplied aggregate counts without scoring affection, intent, compatibility, or personality. |
| audit_chat_claimB | Check whether a proposed interpretation includes user-supplied evidence, reasonable alternatives, missing context, calibrated confidence, and falsifying checks. |
| get_what_brandon_thinks_resourcesB | Return canonical What Brandon Thinks workflow, example, relationship, or safety resources without fetching external content. |
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 targets a distinct action: resource retrieval, brief construction, signal scoring, and claim auditing. However, build_chat_analysis_brief and audit_chat_claim both involve evidence and gap assessment, which could cause slight confusion in deciding between planning and validation.
All tools use snake_case with a verb-first pattern (get_, build_, score_, audit_). The longer noun phrase in get_what_brandon_thinks_resources is the only variation, but it remains consistent with the overall convention.
Four tools is well-scoped for this specialized chat-analysis workflow. Each tool covers a distinct step without redundancy, fitting comfortably within the ideal 3-15 range.
The tool set covers the full analytical lifecycle: retrieving reference resources, structuring a privacy-preserving brief, calculating interaction signals, and auditing a proposed interpretation. No obvious gaps exist for the stated privacy-focused domain.