Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
Omni Coder Dashboard is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
1
downloads a day
local
runs on your machine
41
downloads in 30d
What it does
OCD (Omni Coder Dashboard) — An AI memory engine with real semantic embeddings, 21 MCP tools, cross-tool routing, trace auditing, and proactive IDE interception. 100% local, zero API keys required.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user omni-coder-dashboard-mcp '--' npx -y --package=omni-coder-dashboard ai-dashboard
# 2 — ask your agent for something these tools do
# get_similar_solutions, get_knowledge_context, get_last_session_context and 28 more
Omni Coder Dashboard costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
RIAll 1 server
riko56521 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Omni Coder Dashboard as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user omni-coder-dashboard-mcp '--' npx -y --package=omni-coder-dashboard ai-dashboardReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
31 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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 keyword match.
No parameter schema on file.
Fetch architecture patterns, code conventions, and deep context from the Knowledge Graph.
No parameter schema on file.
Get context from the most recent coding session for continuity.
No parameter schema on file.
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.
No parameter schema on file.
Get a quick efficiency snapshot of your AI coding productivity.
No parameter schema on file.
Get active AI coaching recommendations to improve productivity.
No parameter schema on file.
Get AI development statistics for a specific project.
No parameter schema on file.
Compare AI model performance and cost across your sessions. Models are normalized (e.g., kimi-k2.5 variants are merged).
No parameter schema on file.
Save a critical handoff note or architectural decision for future AI agents.
No parameter schema on file.
Get data-driven guidance on optimal prompt structure based on your history.
No parameter schema on file.
Get a summary of AI coding activity grouped by topic.
No parameter schema on file.
Get explicit
No parameter schema on file.
Get a cost-routing recommendation: should this task use a free local model (Ollama) or a premium cloud model? Returns mathematically proven savings estimate.
No parameter schema on file.
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.
No parameter schema on file.
Manually submit a stack trace or error output for instant proactive analysis. OCD will search its memory and return the best matching past solution.
No parameter schema on file.
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 velocity tracking.
No parameter schema on file.
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.
No parameter schema on file.
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 nudges based on your historical usage patterns. Call this periodically to stay ahead of quality degradation.
No parameter schema on file.
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.
No parameter schema on file.
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 task.
No parameter schema on file.
Update the status of the current OCD task. Use this to mark tasks as completed, paused, or to set a new active task.
No parameter schema on file.
Run a Trace-to-Evidence audit: accepts a question (e.g.
No parameter schema on file.
List available audit templates for the Trace-to-Evidence system. Templates define evidence-gathering strategies for common audit patterns (mapping validation, ingestion throttling, fallback behavior).
No parameter schema on file.
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 problems.
No parameter schema on file.
No parameter schema on file.
Check session health for overrun, tool call repetition, and anti-hallucination risks. Returns verdicts (allow/warn/block). Works from any IDE.
No parameter schema on file.
Log a tool call for repetition tracking. Use from IDEs without hook-based interception.
No parameter schema on file.
Get the OCD Session Guard KPI effectiveness matrix — intervention counts, token savings, quality impact, repetition loops broken, and hallucination prevention. Shows how much value the guard is delivering.
No parameter schema on file.
Session Governor: checks if the current session has hit convergence limits (turns, output tokens, duration, errors). Returns continue/checkpoint/hard_stop with actionable instructions. Call this periodically or when the session feels long.
No parameter schema on file.
Session Governor statistics: checkpoint history, hard stops, overrides, most common triggers, current thresholds. Use to understand session governance patterns.
No parameter schema on file.
Configure Session Governor thresholds for a project. Only set fields you want to override; others keep defaults.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under AGPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Omni Coder Dashboard or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 5.5.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings12 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest28ef9cf38469d2f842c18415394e86bb6ef0a96c09b134c7e18e0bd0b462db5e
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (24 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_similar_solutions | no tags | |
| get_knowledge_context | untrusted-input | untrusted-input: keyword "fetch" |
| get_last_session_context | no tags | |
| get_routing_recommendation | no tags | |
| get_efficiency_snapshot | no tags | |
| get_active_recommendations | no tags | |
| get_project_stats | no tags | |
| get_model_comparison | no tags | |
| push_handoff_note | state-write | state-write: handler runs a INSERT statement at apps/server/dist/mcp-handoff.js:469 |
| get_optimal_prompt_structure | no tags | |
| get_topic_summary | no tags | |
| get_negative_constraints | no tags | |
| get_arbitrage_recommendation | no tags | |
| get_team_memory | no tags | |
| submit_ide_trace | no tags | |
| get_attribution_report | no tags | |
| get_efficiency_tips | no tags | |
| get_session_health_check | no tags | |
| get_current_task | no tags | |
| park_out_of_scope_idea | state-write | state-write: handler runs a INSERT statement at apps/server/dist/mcp-handoff.js:748 |
| update_task_status | state-write | state-write: handler runs a UPDATE statement at apps/server/dist/mcp-handoff.js:768, handler runs a INSERT statement at apps/server/dist/mcp-handoff.js:791 |
| run_trace_audit | no tags | |
| get_audit_templates | no tags | |
| get_audit_history | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest28ef9cf38469d2f8
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 5.5.0. Pin a release below and the command asks for exactly that one.
5.5.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Omni Coder Dashboard can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.