data-ai MCP Server
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch real bugs get picked more often. Agents that hallucinate get deprioritized. MCP server for Claude Code, Cursor, and other IDEs.
Discovered via github-topic:mcp and last synced 1w ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
D[reward signal] C -->
What happens
Time
Feed native agent results back into the pipeline
How
Direct API access without the subscription path
System status, dashboard URL, agent list
Relay
Claude picks agents and dispatches them in parallel
What it shows
Record or retract accuracy signals
`OPENAI_API_KEY` (+ optional `OPENAI_BASE_URL`)
Multi-agent dispatch: `single`, `parallel`, or `consensus`
Save session context for the next session
Built-in 429 watcher falls back to native on cooldown
Create or update an agent team
File a GitHub issue from an in-session bug report
— (local gateway)
Search an agent's cognitive memory
Claude reads UNVERIFIED findings against the code, decides if they're real
Native agents
Feed native cross-review results into consensus
List all available tools
Develop, bind, unbind, or list per-agent skills
Check for / apply gossipcat updates from npm
Relay-only (planned)
Yes
Check in-progress task status
Internal LLM for routing, planning, synthesis (set `provider: "none"` on Claude Code / Cursor to let the host classify natively)
Status
No
Check a memory claim against current code (FRESH / STALE / CONTRADICTED) before acting on backlog
Synthesis-only model that merges cross-review results (does not grade)
Description
No
Self-terminate so the host respawns with a fresh bundle (dev loop)
Decompose a task into sub-tasks with agent assignments
Stream signals as agents emit them (catches pipeline drops mid-round)
Memory compaction, gossip, lens generation
Required per provider
OS keychain via `key_ref`
~1s
30s–1min
What it does
Purpose
Single-agent dispatch with auto agent selection
Collect results with optional cross-review synthesis
View agent accuracy, uniqueness, dispatch weights
Mark consensus findings resolved/open
Ask the dashboard a structured single/multi-select question
Print the gossipcat handbook for humans
Manage runtime feature-gate flags
Return the canonical `<agent_finding>` output format block
`gossip_relay`, `gossip_relay_cross_review`, `reply` — used internally to feed native results + the chat bridge back into the pipeline; you never call these
Means
insight` (invariant #8 in `docs/HANDBOOK.md`); the `gossip_signals` receipt surfaces the drop and a `finding_dropped_format` signal. If you see `<agent_finding>` instead of raw tags, a transport layer is entity-encoding output — pass agent output verbatim to `gossip_relay`. **Multiple IDE instances** — each gets its own dynamic port. For a stable port on one project, set `GOSSIPCAT_PORT=24420` in that environment. **Uninstall** — `npm uninstall -g gossipcat && claude mcp remove gossipcat -s user`; `rm -rf ~/.gossip` (global state) or `<project>/.gossip` (per-project). **Still stuck?** [Open an issue](https://github.com/gossipcat-ai/gossipcat-ai/issues) with the last 100 lines of `.gossip/mcp.log` + `gossip_status` output, or ask in-session *"file a gossipcat bug report about …"* (`gossip_bug_feedback` packages it). <br/> ## Configuration Most of `.gossip/config.json` is **auto-generated by `gossip_setup()`** — hand-edit only to change providers/models/endpoints. First-run defaults work for most projects. Config is searched: `.gossip/config.json` → `gossip.agents.json` → `gossip.agents.yaml`. ```json { "main_agent": { "provider": "google", "model": "gemini-2.5-pro" }, "utility_model": { "provider": "native", "model": "haiku" }, "consensus_judge": { "provider": "anthropic", "model": "claude-sonnet-4-6", "native": true }, "agents": { "sonnet-reviewer": { "provider": "anthropic", "model": "claude-sonnet-4-6", "preset": "reviewer", "skills": ["code_review", "security_audit", "typescript"], "native": true } } } ```