"Finding People on LinkedIn" matching MCP servers:

An MCP server that gives AI agents a private, durable memory of people, providing a personal people graph in PostgreSQL with tools to search, remember, and connect people, plus imports from LinkedIn, Google Contacts, and WhatsApp, and a browser UI.

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

A modular monolith MCP server connecting multiple providers (Redash, PostgreSQL, GitHub) with unified permission, security, and auditing, enabling secure data access and tool execution.

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

Double-entry books an agent keeps as the user, on your own Postgres or Supabase: invoices, VAT returns, bank reconciliation, financial statements and 130 country packs.

This read-only MCP Server allows you to connect to Act-On data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp

Enables governed interaction with synthetic people data through MCP tools, providing per-caller scoped access, semantic-layer metrics, and read-only SQL with authorization checks.

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

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

MCP server for querying a database of 1 million Korean personas with full-text search, enabling AI agents to retrieve detailed demographic, professional, and personal profiles.

Exposes nine governed analytics tools — attrition, headcount, tenure, salary, promotion, and more — plus a restricted read-only SQL execution path, so an HR analyst's plain-English question resolves to a versioned, reproducible method instead of free-form LLM-written SQL. Tool selection is driven by the LLM, while role-based access control, PII screening, SQL guards, result validation, and audit logging keep every answer within policy.

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

A FastMCP server that provides tools for querying and filtering people data from Planning Center People API, enabling access to member information, background checks, roles, and other demographic data.

A read-only MCP server for ServiceNow that provides deep visibility across multiple instances via query, schema inspection, identity, workflow, and code search tools.

Enables AI agents to run deterministic database intelligence tasks including natural-language-to-SQL synthesis, AST SQL auditing and optimization, schema migration diffing, SQL transpilation, index and normalization advice, PII scrubbing, fixture generation, connection-pool sizing, isolation-hazard auditing, and ORM model compilation over Streamable HTTP or stdio.

Provides AI agents read-only access to the Autotask Report Data Warehouse for cross-client reporting on finance, contracts, projects, time, and tickets through schema exploration and SQL queries.

Check 22,000+ devices with open firmware or open protocols (OpenWrt, LineageOS, coreboot, Zigbee2MQTT, Tasmota…) before reverse engineering one; claim a device while you work on it and publish your findings when done.

Guardrail proxy for AI agents on SQL Server. Each statement runs as the caller's own login, a T-SQL parser blocks dangerous statements, and every statement is audited. Local stdio mode or a central Docker service.

Enables AI assistants to execute arbitrary SQL queries on a local SQLite database via a single execute_sql tool.

Enables AI to execute SQL queries (SELECT, DML, DDL) on MySQL/MariaDB databases with strong security: connection credentials never exposed to AI, write queries require user approval, read-only connections enforced, and query results limited to 50 rows.