MCP servers / mcp-clickhouse
mcp-clickhouse
4 of its last 5 updates changed what the agent reads: 5 tool descriptions rewritten, up to 0.7.0.
PyPI package · last recorded on 13 November 2026 on a clean machine with placeholder settings; only tools/list was sent. A changed description is not a vulnerability. PyPI page · Method and limits · this data as JSON.
Release by release
0.5.0 → 0.6.0
minor release, 3 September 2026list_databases: input schema changed
list_tables: description and input schema changed
run_query: input schema changed
0.4.1 → 0.5.0
minor release, 1 September 2026list_tables: description and input schema changed
run_query: description changed
0.4.0 → 0.4.1
patch release, 17 July 2026No tool definition changed.
0.3.0 → 0.4.0
minor release, 3 June 2026list_databases: title, annotations or output schema changed
list_tables: description changed
run_query: title, annotations or output schema changed
Releases tried: 0.3.0 (2026-04-14); 0.4.0 (2026-06-03); 0.4.1 (2026-07-17); 0.5.0 (2026-09-01); 0.6.0 (2026-09-03); 0.7.0 (2026-09-21).
Tools in 0.7.0
The pin is the SHA-256 of the tool's name, description and input schema, as verfy.lock records it. The same pin in your lock means your agent reads this exact definition. Verfy 0.16.0 and later also pin a tool's title, annotations and output schema when the server sends them, so such a tool shows a different pin in your lock.
| Tool | Description | Pin |
|---|---|---|
| list_databases | List available ClickHouse databases | c457a294b7a2 |
| list_tables | List available ClickHouse tables in a database, including schema, comment, row count, and column count. Integers outside [-9007199254740991, 9007199254740991] in table metadata are returned as decimal strings. Pagination tokens are single-use and retained for up to one hour. | 53815e4b864d |
| run_query | Execute SQL queries in ClickHouse. Queries run in read-only mode by default. Bind optional params by name with {name:Type} placeholders, such as {name:String} or {vector:Array(Float32)}. Values may be JSON scalars, nulls, or arrays. Pass exact large integers as decimal strings. JSON lists and objects cannot bind to Tuple and Map types. Python percent formatting and $name$ raw binary parameters are not supported. Parameter values stay out of the MCP server's normal SQL log lines, but may appear in errors and backend logs. Set CLICKHOUSE_ALLOW_WRITE_ACCESS=true to allow DDL and DML operations. Set CLICKHOUSE_ALLOW_DROP=true to additionally allow destructive operations (DROP, TRUNCATE, DELETE, UPDATE, REPLACE TABLE/PARTITION, CREATE OR REPLACE, CLEAR COLUMN/INDEX/PROJECTION, DETACH PERMANENTLY). That gate is a best-effort accident guard, not a security boundary. Integers outside [-9007199254740991, 9007199254740991] are returned as decimal strings. Two optional checks also run through this tool. Use DESCRIBE (<query>) when you need a query's output columns and types; it inspects the result schema and surfaces analysis errors such as an unknown column, but a query that describes cleanly can still fail at runtime. Consider EXPLAIN ESTIMATE <query> before a SELECT that could be expensive; it returns the estimated parts, rows and marks read from MergeTree family tables, which is not run time and not result size. Neither runs the query body, though analysis can execute scalar subqueries. | ba37d9a7c1c2 |
Lock these tools
Pin what mcp-clickhouse serves you today, commit the lock, and a pull request fails when a tool changes, with the text before and after. Pin the package version in your MCP config as well.
$ pip install verfy
$ verfy lock check --update # shows each tool, then writes verfy.lock
$ git add verfy.lock# .github/workflows/verfy.yml, after actions/checkout
- uses: verfy-dev/verfy-action@v1Maintain this server? Run the same check on your releases and add the Locked by Verfy badge to your README.