"Finding Ohad Zafrir's LinkedIn Profile" matching MCP servers:

MCP server that enables AI assistants to search LinkedIn for job posts, save them locally, and manage them via a React dashboard.

Enables MCP clients to register and inspect database instance profiles, record observations and audits, compute scalar and quantile baselines, manage technical-debt findings and incident timelines, link related instances, and import/export sanitized knowledge packages.

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for LinkedIn Ads (beta): https://www.cdata.com/download/download.aspx?sku=EBZK-V&type=beta

This read-only MCP Server allows you to connect to LinkedIn data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Enables AI assistants to query, search, and analyze LinkedIn profiles from the Headstarter network for recruiting, networking, and community building.

Manages LinkedIn prospecting CSV files with deduplication and search, reducing LLM token usage by offloading file operations.

A unified Model Context Protocol server for data engineering and analytics that lets LLM clients query, profile, transform, and visualize data using DuckDB and PySpark, while keeping raw data out of the model's context through read-only, bounded, and audited operations.

Enables querying and updating Markdown frontmatter metadata using DuckDB SQL, with optional semantic search capabilities for finding similar documents based on content.

Gives AI clients guarded access to SAP Business One over SAP HANA / MS SQL and the Service Layer OData API. SQL is read-only, enforced on the server; Service Layer is GET-only by default, with opt-in writes that require user approval unless a profile explicitly turns it off.

Enables PostgreSQL schema exploration and SQL querying through natural language in MCP clients like Cursor, with support for dev/qa profile switching and read-only safety controls.

Enables natural language interaction with PostgreSQL databases via MCP, supporting database exploration, schema listing, and SQL queries with profile-based connections.

A read-only-by-default Model Context Protocol (MCP) server for ClickHouse with schema discovery, parameterized SELECT-only queries, execution-plan analysis, and opt-in writes per profile. Profile-based configuration serves multiple clusters from one toolset deployment.

Enables asking natural-language questions about three published data builds (housing, flights, and a fictional bank), with the agent finding tables, writing SQL, and re-verifying every number against the warehouse before returning an answer.

Enables AI assistants to query Oracle AI Database read-only, profile tables, and render result sets as PNG charts.

Read-only MCP server for SQL Server and PostgreSQL health checks. It runs the codeDB Lens diagnosis (A–F grade with rule coverage, findings with evidence, impact and next actions), reads 24-hour performance recordings, lists databases and tables, describes table schemas, and runs one guarded SELECT at a time within per-profile row and time limits. It uses the user's saved connection profiles; pass

Enables users to ask whether a company is still sponsoring H-1B visas and get markdown tables combining DOL LCA, PERM and USCIS approval/denial data, with six-month trends versus a year earlier and green-card signals per employer. Also supports comparing companies, finding top sponsors by role and location, salary ranges, and disambiguating employer entities, all running locally and offline.

Gives MCP-compatible AI assistants one shared, append-only memory stored as a graph, so facts persist across tools and sessions with their full reasoning chain. Enables finding disagreements between tools, resolving them by recording a winner, and seeing which downstream decisions become stale.

Reviews MySQL migrations, queries and application code before they run, flagging table locks, full table copies, data loss, missing indexes, integer overflow and SQL injection, with a safe rewrite for each finding. Runs locally; your SQL never leaves your machine.

Enables Claude Desktop and Claude Code to read locally synced Fitbit Air health data — scores, trends, sleep, activity, running and body age — run read-only SQL against it, and keep a journal and coach notes on the user's Mac. It also offers profile edits, a refresh tool, and guided prompts such as morning check-ins, weekly reviews, race planning and score explanations.

Runs a local, read-only knowledge graph over MCP, enabling graph queries, path finding, explanations, neighbor exploration, statistics, and god-node discovery without cloud dependencies.