ATLAS MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATLAS_DATA_DIR | No | Override the default data directory (~/.atlas/data/) | ~/.atlas/data/ |
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
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| atlas_onboard_clientA | Create a new client profile for ATLAS advisory. This is the first step in the onboarding process. |
| atlas_get_profileA | Retrieve the full client profile across all advisory lenses — career facts, patterns, goals, accountability, functional data. |
| atlas_update_profileC | Update specific sections of the client profile. |
| atlas_ingest_resumeB | Parse and store career facts extracted from resume text. Claude should extract structured facts before calling this. |
| atlas_ingest_linkedinB | Store LinkedIn profile data for career context building. |
| atlas_ingest_chat_historyB | Analyze past conversation transcripts for behavioral patterns, recurring themes, and psychological insights. |
| atlas_ingest_genetic_dataA | Store SNP/genetic data from services like 23andMe or Ancestry. Focus on SNPs relevant to performance, stress response, sleep, and cognition. |
| atlas_ingest_health_dataC | Store health markers, lab results, sleep data, nutrition logs, or other health-related information. |
| atlas_add_career_factA | Add a single verified career entry — a fact that has been confirmed from a document or directly by the client. |
| atlas_add_patternA | Record an observed behavioral, emotional, or cognitive pattern. Used by the Therapist lens to build psychological context. |
| atlas_add_goalC | Track a new goal with optional milestones and target date. |
| atlas_update_goalC | Update goal status or complete milestones. |
| atlas_track_commitmentA | Log a commitment the client has made, with a deadline for accountability tracking. |
| atlas_complete_commitmentB | Mark a commitment as completed. |
| atlas_review_accountabilityA | Full accountability review — shows all commitments with automatic overdue detection. |
| atlas_log_sessionA | Log an advisory session for continuity. Call this at the end of meaningful conversations. |
| atlas_search_advice_historyA | Search past advice to ensure consistency. Always check before giving advice on topics you've covered before. |
| atlas_analyze_opportunityA | Structured multi-lens opportunity analysis. Returns a framework for evaluating career moves, business decisions, or life changes. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| atlas_initial_intake | Guided onboarding conversation for a new ATLAS client. Walks through data collection across all three lenses. |
| atlas_weekly_review | Weekly accountability and progress review across all active goals and commitments. |
| atlas_opportunity_deep_dive | Full multi-lens analysis of a specific opportunity — career move, business decision, or life change. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| profile_summary | Client profile overview |
| profile_facts | All verified career facts |
| profile_patterns | Observed behavioral and psychological patterns |
| profile_goals | Active goals and milestones |
| profile_accountability | Commitments and accountability tracking |
| profile_functional | Genetic and health optimization data |
| history_sessions | Past advisory session logs |
| history_advice | Past advice log for consistency checking |
TDQS
Scored across 18 tools
Most tools target a distinct resource and action, but a few pairs could cause confusion: atlas_ingest_resume and atlas_add_career_fact both store career facts, and atlas_ingest_chat_history and atlas_add_pattern both relate to behavioral pattern capture. Descriptions help separate bulk ingestion from single verified entries, so the ambiguity is limited.
All tools follow a consistent atlas_verb_noun snake_case pattern. Verbs like ingest, add, get, update, track, complete, log, and search clearly signal the type of operation, and the naming is predictable across the entire set.
18 tools is slightly above the typical 3-15 range, but the server covers a broad multi-lens advisory domain including profile management, data ingestion, goals, commitments, sessions, and analysis. Each tool largely earns its place, though a few ingest/add tools could potentially be consolidated.
The tool surface covers core lifecycle needs: onboarding, profile retrieval/update, multiple data ingestion paths, goal tracking, commitment management, session logging, advice search, and opportunity analysis. Minor gaps exist — there is no delete/remove tool, no commitment update, and no dedicated goal listing beyond profile retrieval — but agents can work around these.