AI Ticketing MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
AI Ticketing MCP
Headless ticketing built for agents: find useful work, claim it safely, recover context, and finish with evidence. Control it through the Model Context Protocol (MCP).
One team, multiple projects, many agents. PostgreSQL is the default implementation; storage, search, and embedding providers are replaceable through exported TypeScript contracts.
What agents get
Structured tickets with acceptance criteria, priorities, capabilities, parents, and blocking dependencies.
Atomic ten-minute claims, heartbeat renewal, stale-worker fencing, and retry-safe mutations.
Durable checkpoints, blocking questions, decisions, and artifact references.
One-call context with complete requirements, project instructions, prior work, and relevant knowledge.
Self, independent-agent, or human verification policies. Independent review is the default.
Hybrid text/vector search, using local Ollama or a hosted OpenAI-compatible embedding provider.
Attributable events and durable polling cursors, without keeping an MCP connection alive.
Local stdio and OAuth-protected Streamable HTTP; no frontend or agent runtime required.
Related MCP server: Helmo
Quickstart
Install Docker with Compose and Node.js 24 or newer. From a clean checkout:
npm ci
node scripts/setup.mjs
docker compose --profile auth --profile local-ai up -d --buildSetup creates private random passwords in the ignored .env file and preserves existing configuration. The first start downloads the embedding model. Check readiness with docker compose ps and docker compose logs model-pull.
MCP:
http://localhost:3000/mcpOAuth metadata:
http://localhost:3000/.well-known/oauth-protected-resource/mcpKeycloak:
http://localhost:8080(administratoradmin, password from your private.env)PostgreSQL: localhost port 5432; roles
ticketing_ownerfor migrations andticketing_appfor runtime.
Run the two-agent walkthrough from the host:
npm run walkthroughIt creates an isolated demo project, connects separate MCP clients, claims work, records a checkpoint, submits evidence, and obtains independent approval. It uses local trusted operator access to register the demo identities. Its final output includes the project and ticket identifiers.
For real users and agents, follow identity and client setup. The realm contains no preconfigured ordinary users and the application grants no permissions automatically.
The work loop
project_listandproject_getdiscover accessible projects and instructions.work_nextfinds eligible work;work_claimacquires it atomically.ticket_contextreturns requirements, blockers, the checkpoint, and relevant sources.ticket_checkpointpreserves progress;work_heartbeatrenews ownership at least every three minutes.ticket_submitsupplies passing evidence for every criterion.ticket_reviewapproves or requests changes according to project policy.
Use a fresh idempotency_key for each logical mutation, reusing it only for an identical retry. Read the latest revision before edits and submission. A changed requirement revokes claims and invalidates affected approvals; an old worker cannot continue with its former token.
Ticket references accept a UUID or readable key such as CORE-42. Project references use UUIDs. Full tool and workflow behavior is documented separately.
Extending the system
import { createApplication } from 'ai-ticketing-mcp';
import type { StorageAdapter, SearchAdapter, EmbeddingProvider } from 'ai-ticketing-mcp/contracts';
const app = createApplication({ storage, search, embeddings });Supply your own adapters and retain the application operations and MCP tools. ai-ticketing-mcp/postgres exports the default adapters; ai-ticketing-mcp/testing exports reusable contract tests. See adapter development for transaction guarantees, migration ownership, and an implementation example.
The package can be consumed from this repository after building; an npm registry release is not required. No alternate production database adapter is advertised until it passes the same tests.
Development and verification
npm ci
npm run build
npm test
# Set TEST_DATABASE_URL to a disposable PostgreSQL database with pgvector.
npm run test:integration
npm run check
npm run format:checkIntegration tests require a real database and fail clearly when it is not configured. They exercise claims, races, retries, stale workers, review policies, permissions, search freshness, and both MCP transports. See the verification record for measured results and operations for backup/restore, rebuilding search, and benchmarks.
Contributions use Conventional Commits. Public MCP and adapter contracts follow semantic versioning. Licensed under Apache-2.0.
Boundaries
The server coordinates work; it does not execute agent commands or independently prove evidence. Binary artifacts stay in external systems. Hosted embedding providers receive indexed text. Retrieval is eventually consistent and reports degraded semantic coverage; authoritative ticket reads remain available while indexing catches up.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Project tracker for AI agents and teams: file, claim, update and hand off tickets over MCP.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Work management where AI agents are first-class members: tasks, projects, memory over hosted MCP
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceLocal-first harness and ticket operations for AI assistants via CLI or MCP.9 npmMIT
- AlicenseNot gradedqualityBmaintenanceA self-hosted work dashboard for AI agent teams, where agents create and manage tickets through MCP tools and humans review an awaiting-human queue backed by an append-only event log. Enables ticket lifecycle management and evidence-based provenance tracking.MIT

agent-taskofficial
FlicenseNot gradedqualityCmaintenanceAgentTask is a governed work platform where human teams and AI agents share one backlog. Hosted remote MCP server (streamable HTTP, OAuth 2.1 or org API keys) with 60+ tools for tasks, subtasks, projects, groups, labels, notes, comments, attachments, search, crews, and agent runs.-- AlicenseNot gradedqualityBmaintenanceEnables development agents to keep persistent memory: proposing and reviewing workspace-scoped content, running hybrid search over accepted sources, and resuming projects with auditable history and provenance. It exposes 32 MCP tools over stdio and authenticated Streamable HTTP, with optional embeddings and rerank.Apache 2.0