Awesome MCPOther MCP Servers

smn2gnt/MCP-Salesforce

⭐ 178 Python added to this list on 2025-05-14 repository created 2024-12-17

MCP Salesforce Connector is a Model Context Protocol server that gives LLM clients structured access to a Salesforce organization. Query tools cover the two Salesforce query languages: run_soql_query executes SOQL statements against specific objects, and run_sosl_search performs SOSL text searches across objects. Metadata tools let a model discover the org before querying it, with list_sobjects returning all available standard and custom objects and get_object_fields returning field names, labels and types for a chosen object. Record operations are available one at a time through get_record, create_record, update_record and delete_record, and in batches through bulk_create_records, bulk_update_records, which requires an Id field on each record, and bulk_delete_records, which takes a list of record identifiers. Three advanced tools reach past the standard data APIs: tooling_execute issues Tooling API requests, apex_execute calls Apex REST endpoints, and restful makes direct REST API calls to any Salesforce resource, which keeps the server useful for endpoints the dedicated tools do not cover. Four authentication methods are supported. The recommended path is OAuth using SALESFORCE_ACCESS_TOKEN together with SALESFORCE_INSTANCE_URL. A client credentials flow using SALESFORCE_CLIENT_ID and SALESFORCE_CLIENT_SECRET is offered for server to server integrations. When no OAuth variables are present the server falls back to the active Salesforce CLI default org in the current workspace, reading it through sf org display or sfdx force:org:display, with SALESFORCE_CLI_TARGET_ORG selecting a specific alias. A legacy username, password and security token combination is the final fallback. Setting SALESFORCE_DOMAIN to test points the connection at a sandbox instead of production. The server is published as mcp-salesforce-connector and is launched through uvx from an MCP host configuration such as claude_desktop_config.json.

https://github.com/smn2gnt/MCP-Salesforce

mcpmcp-serversalesforcecrmsoqlsoslapexrest-apipython

Also in Other MCP Servers

microsoft/markitdown

MarkItDown is a Python tool that converts various file formats into Markdown and integrates with LLM applications via an MCP server for enhanced text analysis and document processing.

punkpeye/awesome-mcp-servers

A curated collection of Model Context Protocol (MCP) servers that enable AI models to securely interact with local and remote resources through standardized server implementations.

modelcontextprotocol/servers

The Model Context Protocol Servers repository offers reference implementations and third-party integrations that demonstrate how MCP enables Large Language Models to securely access and interact with diverse tools and data sources.

koala73/worldmonitor

World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.

headroomlabs-ai/headroom

Headroom is a context compression layer for AI agents, reducing token usage by 60-95% while preserving accuracy, implemented as a library, proxy, and MCP server.

diegosouzapw/OmniRoute

OmniRoute is a free AI gateway that connects various AI tools and models from over 230 providers through a single endpoint, featuring token compression, smart auto-fallback, and support for Model C...

rohitg00/ai-engineering-from-scratch

This comprehensive curriculum teaches AI engineering from scratch, focusing on building AI algorithms, agents, and MCP servers hands-on, covering everything from mathematical foundations to autonom...

every-app/open-seo

Open source, self-hostable SEO platform that exposes its keyword, rank, backlink and site-audit data to AI agents through an MCP server and a set of companion agent skills.