MCP server exposing a SQLMesh project (models, plans, column-level lineage, audits) to LLM agents
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"sqlmesh-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# sqlmesh-mcp [](https://github.com/Zain-ul-Abdin45/sqlmesh-mcp/actions/workflows/ci.yml) [](https://pypi.org/project/sqlmesh-mcp/) [](https://pypi.org/project/sqlmesh-mcp/) [](LICENSE) MCP server exposing a [SQLMesh](https://github.com/SQLMesh/sqlmesh) project to LLM agents: model metadata, bounded data previews, plan previews, column-level lineage, audits/tests, environment diffs, resources, and reusable prompts. Not officially affiliated with SQLMesh or Tobiko Data. ## Why SQLMesh's standout feature is column-level lineage, which is exactly the kind of question an agent is good at answering interactively ("where does `revenue` in `finance.daily_summary` come from?") that a CLI isn't. As of writing, the only prior MCP server for SQLMesh ([`sherman94062/sqlmesh-mcp`](https://github.com/sherman94062/sqlmesh-mcp)) is a small unmaintained side project — this one aims to be documented, tested, and kept current with SQLMesh's API. ## Install ```bash pip install sqlmesh-mcp ``` ## Usage Point it at a SQLMesh project directory: ```json { "mcpServers": { "sqlmesh": { "command": "sqlmesh-mcp", "env": { "SQLMESH_PROJECT_PATH": "/path/to/your/sqlmesh/project" } } } } ``` ## Example Calling `list_models` against [`examples/demo_project`](examples/demo_project) (a stock `sqlmesh init duckdb` project) returns: ```json [ { "name": "sqlmesh_example.full_model", "kind": "FULL", "description": null, "owner": null, "tags": [], "columns": { "item_id": "INT", "num_orders": "BIGINT" } }, { "name": "sqlmesh_example.incremental_model", "kind": "INCREMENTAL_BY_TIME_RANGE", "description": null, "owner": null, "tags": [], "columns": …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.