# Talent-Augmenting Layer MCP server

Personalised AI augmentation system — makes you better at your work, not dependent on AI

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-angelo-leone-talent-augmenting-layer
- Repository: https://github.com/angelo-leone/talent-augmenting-layer

## Install
- Endpoint: https://proworker-hosted.onrender.com/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://proworker-hosted.onrender.com/mcp

## Tools
- talent_get_profile - Load a Talent-Augmenting OS profile by name. Returns the full profile with expertise map, calibration settings, task classification, and red lines. Use this at the start of every conversation. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_get_calibration - Get the Talent-Augmenting OS calibration settings for a user. Returns a compact JSON block suitable for injecting into any LLM system prompt. Includes friction levels, coaching domains, red lines, and interaction preferences. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_classify_task - Classify a task according to the user's Talent-Augmenting OS profile. Returns one of: automate, augment, coach, protect, hands_off: along with the recommended AI behaviour for that task. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_log_interaction - Log an interaction for skill tracking. Call this after substantive AI interactions to track the user's engagement patterns and skill development. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_get_progression - Get skill progression analysis for a user. Shows interaction counts, engagement patterns, domain-level growth/atrophy signals, and warnings about potential de-skilling. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_list_profiles - List all available Talent-Augmenting OS profiles. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_status - Get a comprehensive status report for a user: profile summary, current calibration, skill progression stats, trend direction, atrophy warnings, and recommended next actions. Use this for a quick overview at the start of a conversation. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_org_summary - Get an organisation-level summary across all profiles. Shows aggregate dependency risk, growth potential, expertise distribution, trend alerts, and per-domain skill breakdown. For org dashboards. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_delete_profile - Delete a user's profile and interaction logs. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_save_profile - Save or update a user's profile markdown content. Use this after running /talent-assess to write the generated profile, or after /talent-update to save changes. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_assess_start - Start a Talent-Augmenting OS onboarding assessment. Returns the full assessment protocol with all questions, behavioural anchors, and instructions for how to run the assessment conversationally. The chatbot uses this to ask questions one at a time, collect answers, then call talent_assess_score and talent_assess_create_profile to compute scores and save the profile. Call this at the beginning of any onboarding conversation. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_assess_score - Compute the user's TAOS assessment scores from the numeric answers collected during the assessment conversation. Takes the per-question answers (each 1 to 5) and per-domain expertise ratings, and returns the user's dependency risk, growth potential, AI literacy, expertise summary, and overall TAOS readiness score, with plain-language interpretations and recommended coaching calibration. Call this once all assessment questions have been answered, then pass the result to talent_assess_create_profile. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_assess_create_profile - Generate and save a complete Talent-Augmenting OS profile from assessment data. Call this after talent_assess_score to create the profile file. Takes the computed scores, demographic info, goals, task classifications, and preferences collected during the assessment conversation. Returns the generated profile and saves it to disk. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_suggest_domains - Suggest expertise domains for a user based on their role, industry, and responsibilities. Returns a curated list of domain suggestions with descriptions drawn from an industry-specific taxonomy. Use this during the assessment to help identify relevant domains for the Expertise Self-Assessment (ESA). The LLM has override authority and can add or remove domains from the suggestions. Endpoint: https://proworker-hosted.onrender.com/mcp
- talent_parse_telemetry - Parse <tal_log> telemetry blocks from an LLM response and record them. The system prompt instructs the LLM to emit <tal_log> JSON blocks after each substantive interaction. Call this tool with the full LLM response text to extract and log all telemetry entries. Each entry is saved to the local JSONL interaction log and optionally pushed to the hosted API. Endpoint: https://proworker-hosted.onrender.com/mcp

## Resources
- talent://coaching-modules - Structured coaching session designs for common growth domains MIME type: text/markdown
- talent://framework - Research-backed assessment framework for Talent-Augmenting OS MIME type: text/markdown
- talent://literature - Research backing for Talent-Augmenting OS techniques MIME type: text/markdown

## Prompts
- talent-system - Complete Talent-Augmenting OS system prompt for any LLM. Includes the base instructions + the user's profile. Paste this into any LLM's system prompt to activate Talent-Augmenting OS. Arguments: name
- talent-assess - Run the Talent-Augmenting OS assessment to create a new profile. Arguments: name
- talent-coach - Start a Talent-Augmenting OS coaching session. Arguments: name, focus
- talent-update - Update an existing Talent-Augmenting OS profile based on recent work. Arguments: name

## Metadata
- Owner: io.github.angelo-leone
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Apr 9, 2026
- Source: https://registry.modelcontextprotocol.io