ClickHouse
PYPI · MCP-CLICKHOUSE · 2 COMPONENTS
Official ClickHouse MCP server for querying and exploring ClickHouse clusters and chDB.
Available components
Last scanned (20 hours ago)
Scores higher than 64% of PyPI servers
Category Databases
Recent critical change
CVE-2026-32871 affects this package (4 Aug 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security40
- Malware scan not yet available for this package.Unverified
- CVE check failed: a known medium-severity CVE affects fastmcp 4.0.11, a direct dependency. A fixed version is available. View diagnostics → Fail
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 27 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to ClickHouse/mcp-clickhouse). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 43 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 635 tokens (~211/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
- Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 75% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "run_query" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 −20
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.63 functional
- 31 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 30 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 28 Oct 26 0
- Stability: 0.97 → pass security
- 27 Oct 26 0
- Stability: pass → 0.97 functional
- 24 Oct 26 −3
- GHSA-vqqp-x5qm-5qp4 affects this package: medium ▼ security
- GHSA-7xgj-8392-5q4r affects this package: medium ▼ security
- Known CVEs: pass → fail ▼ security
- 22 Oct 26 +15
- Malware scan: unverified → pass ▲ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed pypi/mcp-clickhouse@0.7.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | ClickHouse/mcp-clickhouse |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/ClickHouse/mcp-clickhouse/.github/workflows/publish.yml@refs/tags/v0.7.0 |
| Rekor log index | 2905898224 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:2168e4ddd3e704ef971c12fb0bb15b85e74470bfa9e3d190a29b8954991e978f |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Vulnerabilities 2 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-7xgj-8392-5q4r | medium | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N | yes | |
| GHSA-vqqp-x5qm-5qp4 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 27 packages
| Packages resolved | 27 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
list_databases List Databases ~15
List available ClickHouse databases
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
list_tables List Tables ~205
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.
| Name | Type | Req | Description |
|---|---|---|---|
| database | string | yes | The database to list tables from |
| include_detailed_columns | boolean | – | Whether to include detailed column metadata (default: True). When False, the columns array will be empty but create_table_query still contains all column information. This reduces payload size for la… |
| like | – | – | Optional LIKE pattern to filter table names |
| not_like | – | – | Optional NOT LIKE pattern to exclude table names |
| page_size | integer | – | Number of tables to return per page (default: 50, must be greater than 0) |
| page_token | – | – | Single-use token from a previous call, retained for up to one hour |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
run_query Run Query ~351
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.
| Name | Type | Req | Description |
|---|---|---|---|
| params | – | – | – |
| query | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the ClickHouse MCP server?
ClickHouse runs locally as a PyPI package, launched with uvx mcp-clickhouse. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mcp-clickhouse
claude mcp add clickhouse-mcp-clickhouse -- uvx mcp-clickhouse
What is the ClickHouse MCP server?
ClickHouse is an MCP server listed in the public MCP registry as io.github.ClickHouse/mcp-clickhouse. Official ClickHouse MCP server for querying and exploring ClickHouse clusters and chDB. This page covers its PyPI package (mcp-clickhouse).
Is the ClickHouse MCP server safe to use?
ClickHouse scores 69 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 4 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ClickHouse MCP server expose?
ClickHouse exposes 3 tools: list_databases, list_tables, run_query. Their descriptions and schemas cost roughly 571 tokens of context every time the server is loaded.
Is the ClickHouse MCP server still maintained?
ClickHouse is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the ClickHouse MCP server under?
ClickHouse declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.