mcpserver.lol
registry/ocd
Connection check local install

ocd

OCD (Omni Coder Dashboard) v5.6.0 — AI memory engine with real semantic embeddings, 25 MCP tools, session guard, trace-to-evidence audit bot, Antigravity intelligence, cost visibility, smart routing, and proactive IDE interception. 100% local, zero API keys.

Tools 24
GitHub stars 3
Installs / wk 12
Licence
Transport stdio
Last checked never

Tools & capabilities

24 tools

Read from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.

get_active_recommendations from source
Get active AI coaching recommendations to improve productivity.
get_arbitrage_recommendation from source
Get a cost-routing recommendation: should this task use a free local model (Ollama) or a premium cloud model? Returns mathematically proven savings estimate.
get_attribution_report from source
Get an AI vs. human code authorship breakdown for commits. Shows per-project, per-branch, and per-tool attribution percentages for engineering managers, compliance reporting, and v…
get_audit_history from source
Retrieve past Trace-to-Evidence audit runs and their results. Useful for tracking recurring issues, comparing audit outcomes across sessions, and avoiding re-investigating solved p…
get_audit_templates from source
List available audit templates for the Trace-to-Evidence system. Templates define evidence-gathering strategies for common audit patterns (mapping validation, ingestion throttling,…
get_current_task from source
CRITICAL: Call this tool before starting any new action to understand the current scope. Returns the active task from OCD so you do not deviate or cause scope creep.
get_efficiency_snapshot from source
Get a quick efficiency snapshot of your AI coding productivity.
get_efficiency_tips from source
Get personalized token-saving tips based on your usage patterns. Returns your daily burn rate, weekly forecast, top token consumers, and actionable quick wins to reduce waste.
get_knowledge_context from source
Fetch architecture patterns, code conventions, and deep context from the Knowledge Graph.
get_last_session_context from source
Get context from the most recent coding session for continuity.
get_model_comparison from source
Compare AI model performance and cost across your sessions. Models are normalized (e.g., kimi-k2.5 variants are merged).
get_negative_constraints from source
Get explicit
get_optimal_prompt_structure from source
Get data-driven guidance on optimal prompt structure based on your history.
get_project_stats from source
Get AI development statistics for a specific project.
get_routing_recommendation from source
Get which AI tool + model is statistically best for your current task type. For single-tool users, provides model-level optimization and workflow tips instead of cross-tool routing…
get_session_health_check from source
Check your current session health using cross-session patterns. Returns a status (healthy/degrading/critical), a suggested action (continue/compact/new_session), and context-aware…
get_similar_solutions from source
Search the semantic memory bank for successful code implementations from past coding sessions. Uses real vector similarity (ONNX/Ollama/OpenAI) — results labeled as semantic or key…
get_team_memory from source
Retrieve solutions that teammates on the same local network discovered in their OCD instances. Requires P2P_SECRET env var to be set on all nodes.
get_topic_summary from source
Get a summary of AI coding activity grouped by topic.
park_out_of_scope_idea from source
Call this when the user suggests an idea that does not directly contribute to the current active task. Parks the idea in OCD so it is not lost, then redirects focus back to the tas…
push_handoff_note from source
Save a critical handoff note or architectural decision for future AI agents.
run_trace_audit from source
Run a Trace-to-Evidence audit: accepts a question (e.g.
submit_ide_trace from source
Manually submit a stack trace or error output for instant proactive analysis. OCD will search its memory and return the best matching past solution.
update_task_status from source
Update the status of the current OCD task. Use this to mark tasks as completed, paused, or to set a new active task.