Data workflows · skills · 18 picks

Claude skills and MCP tools for data workflows

Claude skills, MCP servers, and tools for data extraction, SQL, analytics, spreadsheet workflows, enrichment, and reporting.

Curated by @heyclaude-editors Updated 2026-07-18

Claude skills, MCP servers, and tools for data extraction, SQL, analytics, spreadsheet workflows, enrichment, and reporting.

Compared at a glance

The top 5 picks side by side on trust, install, platform support, and disclosed notes — full rationale for each below.

3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).

Next steps differ across picks — use the actions in the table below to copy install commands and source links per resource.

Field	Postgresql MCP Server - MCP Servers Official MCP server providing read-only access to PostgreSQL databases with schema inspection and query capabilities Open dossier	PostgreSQL Query Optimization Skill Analyze and optimize PostgreSQL queries for OLTP and OLAP workloads with AI-assisted performance tuning, indexing strategies, and execution plan analysis. Open dossier	ClickHouse MCP Server for Claude Connect Claude to ClickHouse for read-only SQL exploration, schema discovery, and safe analytics workflows. Open dossier	DuckDB MCP Server MCP server for querying a local DuckDB database file from Claude through a single SQL query tool, with optional DuckDB-native read-only mode. Open dossier	StarRocks MCP Server Official StarRocks MCP server for SQL execution, database exploration, StarRocks resource templates, system information, table/database overviews, and Plotly chart generation. Open dossier
Next stepsDiffers	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing	Open dossier API JSON Open LLM Open source Newsletter Claim listing	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing
Trust
Review status	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed
Package trustDiffers	Package verified	Package verified2025-10-16	Package not verified	Package not verified	Package not verified
Source provenanceDiffers	No submission link	No submission link	Source-backed	Source-backed	Source-backed
SubmitterDiffers	—	—	oktofeesh1	oktofeesh1	oktofeesh1
Install risk	Low risk	Low risk	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Brand	Anthropic	—	—	—	StarRocks
Category	mcp	skills	mcp	mcp	mcp
Source	First-party	First-party	Source-backed	Source-backed	Source-backed
Author	Anthropic	JSONbored	ClickHouse	ktanaka101	StarRocks
Added	2025-09-16	2025-10-16	2026-06-03	2026-06-06	2026-06-06
Platforms	Claude Code Claude Desktop	Claude Code Codex Windsurf Gemini Cursor CLI	Claude Code Claude Desktop	Claude Code Claude Desktop	Claude Code Claude Desktop
Harness	Claude Code Claude Desktop	Claude Code Codex Windsurf Gemini Cursor CLI	Claude Code Claude Desktop	Claude Code Claude Desktop	Claude Code Claude Desktop
Source repo	—	—	—	—	—
Safety notes	✓Use a read-only database user with restricted schemas unless write access is explicitly needed and reviewed.	✓Setup downloads/unzips a package, and the skill connects to your database to run EXPLAIN ANALYZE and create indexes; index builds and config changes can lock tables and affect production — test against a replica or staging first.	✓The upstream server runs ClickHouse queries in read-only mode by default because `CLICKHOUSE_ALLOW_WRITE_ACCESS` is false unless explicitly enabled. Leave write access disabled for production investigation workflows. If write access is enabled, destructive operations such as DROP and TRUNCATE require the additional `CLICKHOUSE_ALLOW_DROP` opt-in. Treat both flags as privileged operational changes, not normal client configuration. Use a dedicated least-privilege ClickHouse user or role. MCP read-only mode does not hide tables, columns, rows, or system metadata that the database account is already allowed to read. Review model-generated SQL before execution, especially broad table scans, expensive aggregations, cross-database queries, or wide time ranges against production clusters. For HTTP or SSE transports, keep authentication enabled. The upstream server requires authentication by default for those transports and only documents disabling it for local development.	✓The server exposes a single `query` tool that can execute any valid DuckDB SQL statement against the configured database. Without `--readonly`, the server can create the database file, create tables, insert data, update rows, delete rows, and mutate database state. With `--readonly`, the server opens DuckDB with native read-only protection and fails to start if the database file or parent directory is missing. The `--keep-connection` option can hold a persistent DuckDB connection and file lock for the server lifetime. Treat SQL generated by a model as executable code; review queries before running them on important data.	✓StarRocks MCP can execute SQL through `read_query` and DDL/DML through `write_query`. The `write_query` tool is documented for CREATE, ALTER, DROP, INSERT, UPDATE, DELETE, and other commands that do not return a result set. The `read_query` tool can write full query results to files when `output_file` is provided; relative paths use STARROCKS_MCP_OUTPUT_DIR, while absolute and home-relative paths bypass that directory. Overview tools can sample rows, count rows, cache table summaries in memory, and return cached errors or stale summaries until refreshed. The `query_and_plotly_chart` tool executes a SQL query and uses a Python Plotly expression to generate chart output from the result DataFrame. Resource templates can expose database, table, proc, transaction, job, task, catalog, frontend, backend, and compute-node information. SSE mode is documented as deprecated; prefer stdio or streamable HTTP with explicit network controls.
Privacy notes	✓Queried schemas, table names, rows, connection details, and application data may be exposed through tool calls.	✓Query analysis can surface table/column names and sample row values from your database; keep connection strings and credentials in environment variables and review what plans/output you share.	✓Query results, database names, table names, column metadata, create-table definitions, and aggregate outputs can become visible to the connected MCP client and model session. ClickHouse data often includes logs, events, analytics records, user identifiers, IP addresses, request payloads, or product usage data; use database permissions and query limits before exposing production datasets. Store ClickHouse passwords, roles, and bearer tokens in MCP environment configuration or your client secret-management flow, not in prompts or checked-in configuration files. chDB support can query local files, URLs, and embedded datasets when enabled. Keep it disabled unless that local data access is intentional.	✓Tool calls and results can expose database paths, table names, schemas, query text, row values, file paths referenced by SQL, and analytical results to the MCP client and model provider. DuckDB can query local files and extensions depending on SQL, configuration, and installed capabilities; keep the server scoped to approved data directories. Do not point writable sessions at production, customer, regulated, or irreplaceable DuckDB files without backups and explicit approval. Query errors can reveal schema names, file paths, and data-shape details.	✓StarRocks credentials, connection URLs, database names, table names, schemas, SQL text, query results, sample rows, proc output, generated chart images, errors, and output-file paths may be visible to the MCP client and model provider. StarRocks datasets can contain customer records, telemetry, analytics, business metrics, security data, billing data, or other regulated information. Output files created by `read_query` remain on the machine where the MCP server runs, which may be local for desktop clients or remote for HTTP deployments. STARROCKS_URL, STARROCKS_PASSWORD, Keychain service names, database credentials, and generated result files should stay out of prompts, issues, logs, screenshots, and committed files.
Prerequisites	PostgreSQL database (local or remote PostgreSQL server) PostgreSQL connection string (PostgreSQL connection URI with user, password, host, port, and database format) Node.js and npx (for running @modelcontextprotocol/server-postgres package) Network access (if connecting to remote PostgreSQL server)	PostgreSQL 14+ (16+ recommended) pg_stat_statements extension EXPLAIN access permissions psql or database client	uv available for the documented `uv run --with mcp-clickhouse` launch path, or Python 3.10+ with the `mcp-clickhouse` package installed ClickHouse Cloud or self-hosted ClickHouse reachable from the MCP server Dedicated ClickHouse user with the minimum read permissions needed for the intended databases and tables Claude Code, Claude Desktop, Cursor, VS Code, or another MCP-capable client	Python and `uvx` available to the MCP client runtime. Existing DuckDB database file when using `--readonly`. Path to a DuckDB database file that Claude is allowed to query. Decision on whether the server should run in read-only mode before connecting it to an agent.	Python 3.10 or newer and uv available to the MCP client runtime. StarRocks FE host, MySQL protocol port, database, username, and password. Least-privilege StarRocks user with only the approved databases and operations. Written policy for whether `write_query` may be used in the workspace.
Install	`claude mcp list && claude mcp status postgres`	`curl -L https://heyclau.de/downloads/skills/postgresql-query-optimization.zip -o postgresql-query-optimization.zip && unzip -o postgresql-query-optimization.zip -d ./postgresql-query-optimization`	`claude mcp add clickhouse --env CLICKHOUSE_HOST=YOUR_CLICKHOUSE_HOST --env CLICKHOUSE_PORT=8443 --env CLICKHOUSE_USER=YOUR_CLICKHOUSE_USER --env CLICKHOUSE_PASSWORD=YOUR_CLICKHOUSE_PASSWORD --env CLICKHOUSE_SECURE=true --env CLICKHOUSE_VERIFY=true -- uv run --with mcp-clickhouse --python 3.10 mcp-clickhouse`	`uvx mcp-server-duckdb --db-path ./data.duckdb --readonly`	`uv run --with mcp-server-starrocks mcp-server-starrocks`
Config	`Manual-only setup: { "postgres": { "args": [ "-y", "@modelcontextprotocol/server-postgres", "postgresql://localhost/mydb" ], "command": "npx" } }`	—	`Manual-only setup: { "clickhouse": { "command": "uv", "args": ["run", "--with", "mcp-clickhouse", "--python", "3.10", "mcp-clickhouse"], "env": { "CLICKHOUSE_HOST": "<clickhouse-host>", "CLICKHOUSE_PORT": "8443", "CLICKHOUSE_USER": "<clickhouse-user>", "CLICKHOUSE_PASSWORD": "<clickhouse-password>", "CLICKHOUSE_SECURE": "true", "CLICKHOUSE_VERIFY": "true", "CLICKHOUSE_CONNECT_TIMEOUT": "30", "CLICKHOUSE_SEND_RECEIVE_TIMEOUT": "30" } } }`	`{ "mcpServers": { "duckdb": { "command": "uvx", "args": ["mcp-server-duckdb", "--db-path", "./data.duckdb", "--readonly"] } } }`	`{ "mcpServers": { "starrocks": { "command": "uv", "args": ["run", "--with", "mcp-server-starrocks", "mcp-server-starrocks"], "env": { "STARROCKS_HOST": "<starrocks-fe-host>", "STARROCKS_PORT": "9030", "STARROCKS_USER": "<least-privilege-user>", "STARROCKS_PASSWORD": "<starrocks-password>", "STARROCKS_DB": "<approved-database>", "MCP_TRANSPORT_MODE": "stdio", "STARROCKS_MCP_OUTPUT_DIR": "<approved-output-dir>" } } } }`
Citations	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationmodelcontextprotocol.io Package (SHA-256 pinned)/downloads/mcp/postgresql-mcp-server.mcpb Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationpostgresql.org Package (SHA-256 pinned)/downloads/skills/postgresql-query-optimization.zip Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-03 Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-06 Source methodology →
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed	Unclaimed