data quality mcp servers

28 tagged data quality, measured the same way as everything else here.

Browse within: data-engineering 14

codebase-memory

01

benseverndev-oss/goldenmatch

MCP server Claude CodeCodexCursor +2

MCP server "codebase-memory" as configured in benseverndev-oss/goldenmatch. Launched with codebase-memory-mcp.

129 2d ago A tokens not measured original MIT

goldenanalysis

02

benseverndev-oss/goldenmatch

MCP server Claude CodeCodexCursor +2

Read-only cross-cutting analysis, metrics, and reporting engine for the Golden Suite. Runs locally from the goldenanalysis Python package.

129 2d ago A tokens not measured original MIT

goldenmatch

03

benseverndev-oss/goldenmatch

MCP server Claude CodeCodexCursor +2

Entity resolution toolkit — deduplicate records, match across sources, and maintain golden records. Runs locally from the goldenmatch Python package.

129 2d ago A tokens not measured original MIT

datanav

04

hike-lab/public-data-lens

MCP server Claude CodeCodexCursor +2

MCP server "datanav" as configured in hike-lab/public-data-lens. Runs datanav.api.mcp_server with .venv/bin/python. Needs 1 environment variable to run.

81 7d ago A tokens not measured original MIT

scherlok

05

rbmuller/scherlok

MCP server Claude CodeCodexCursor +2

A detective for your data. Zero-config data quality monitoring. Runs locally from the scherlok Python package. Needs 1 environment variable to run.

9 6d ago A tokens not measured original MIT

trustydata

06

htristram/trustydata-mcp-server

MCP server Claude CodeCodexCursor +2

French address quality, geocoding & routing from official data (BAN, INSEE, OpenStreetMap). Remote server at mcp.trustydata.app.

3 1mo ago A tokens not measured original MIT

datasentry

08

Jackxiaozhiren/datasentry

MCP server Claude CodeCodexCursor +2

Find, explain, and safely fix bad data with local-first detection, evidence-backed issues, and reversible repairs. Runs locally from the datasentry-ai Python package.

2 3d ago A tokens not measured original Apache-2.0

goldencheck

09

benseverndev-oss/goldencheck

MCP server Claude CodeCodexCursor +2

Data validation that discovers rules from your data so you don't have to write them. Runs locally from the goldencheck Python package.

2 4mo ago A tokens not measured original MIT archived

data-profiler-mcp

10

haiiibin/data-profiler-mcp

MCP server Claude CodeCodexCursor

MCP server that profiles tabular data files (CSV, TSV, Parquet, Excel, JSON): schema, distributions, data-quality flags, and dtype suggestions for LLM agents. Runs locally from the data-profiler-mcp Python package.

2 10d ago A tokens not measured original MIT

mcp-data-profiler

11

Ridadata/mcp-data-profiler

MCP server Claude CodeCodexCursor

MCP server that profiles local datasets (CSV, Parquet, JSON, Excel) so AI agents can understand data without reading raw rows. Runs locally from the mcp-data-profiler Python package.

1 24d ago A tokens not measured original MIT

goldenflow

12

benseverndev-oss/goldenflow

MCP server Claude CodeCodexCursor

Data transformation toolkit — standardize, reshape, and normalize messy data before it hits your pipeline. Runs locally from the goldenflow Python package.

1 4mo ago A tokens not measured original MIT archived

andon

13

gulmezeren2-byte/andon

MCP server Claude CodeCodexCursor

Deterministic verification for AI-generated analysis. Stop the line when the numbers don't add up. Runs locally from the andon-verify Python package.

1 28d ago A tokens not measured original MIT

papasega/african-speech-mcp

MCP server Claude CodeCodexCursor

Quality-aware read-only MCP server for Wolof speech corpus selection. Runs locally from the african-speech-mcp Python package. Needs 4 environment variables to run.

1 5d ago A tokens not measured original Apache-2.0

praxis

15

Marc-Dvci/praxis-datahub

MCP server Claude CodeCodexCursor

MCP server "praxis" as configured in Marc-Dvci/praxis-datahub. Runs praxis.mcp with python. Needs 1 environment variable to run.

0 22d ago A tokens not measured original Apache-2.0

datahub

16

Marc-Dvci/praxis-datahub

MCP server Claude CodeCodexCursor

MCP server "datahub" as configured in Marc-Dvci/praxis-datahub. Runs locally from the mcp-server-datahub@latest Python package. Needs 2 environment variables to run.

0 22d ago A tokens not measured original Apache-2.0

scrapecheck

17

FieldmodeLLC/scrapecheck-mcp

MCP server Claude CodeCodexCursor

Verify before your agent acts on data it paid for. Signed verdicts, checkable offline, via x402. Remote server at scrapecheck-mcp.fly.dev.

0 2d ago A tokens not measured original MIT

agent-output-guard

18

agenson-tools/agent-output-guard-mcp

MCP server Claude CodeCodexCursor

Validate and verify data from other agents before acting on it. Zero LLM costs. Runs locally from the @agenson-horrowitz/agent-output-guard-mcp npm package.

0 4mo ago A tokens not measured original MIT

infermap

19

benseverndev-oss/infermap

MCP server Claude CodeCodexCursor

Inference-driven schema mapping engine. Runs locally from the infermap Python package.

0 4mo ago A tokens not measured original MIT archived

datapulse-my

20

r3dz4r/datapulse-my

MCP server Claude CodeCodexCursor

Read-only discovery for 389 Malaysian public datasets with freshness, licence, and provenance. Remote server at mcp.data-pulse.my.

0 yesterday A tokens not measured original MIT

datahub-polygraph

21

kishanraj41/datahub-polygraph

MCP server Claude CodeCodexCursor

MCP server "datahub-polygraph" as configured in kishanraj41/datahub-polygraph. Runs locally from the datahub-polygraph Python package.

0 22d ago A tokens not measured original Apache-2.0

sqlproctor

22

debabsah/sqlproctor

MCP server Claude CodeCodexCursor +2

Deterministic semantic verification for agent-generated SQL. Runs locally from the sqlproctor Python package.

0 1mo ago A tokens not measured original MIT

web-data-mcp

23

fctpe/web-data-mcp

MCP server Claude CodeCodexCursor +2

MCP server "web-data-mcp" as configured in fctpe/web-data-mcp. Runs locally from the web-data-mcp npm package. Needs 2 environment variables to run.

0 27d ago A tokens not measured original MIT

nightshift

24

Mossab28/nightshift

MCP server Claude CodeCodexCursor +2

A python library and command line program for plotting simulated 2D and 3D NMR spectra from assigned chemical shifts from the BMRB. Runs locally from the nightshift Python package.

0 22d ago A tokens not measured original Apache-2.0