"salesforce" matching MCP servers:

Enables Salesforce lead and permission set management through natural language. Supports creating leads, creating permission sets, and assigning permission sets to users via the Model Context Protocol.

Analyzes Salesforce permission architecture (profiles, permission sets, groups) to support RBAC remediation. It snapshots the permission model into DuckDB and provides tools for diffs, sensitive access detection, and verified decomposition proposals.

MCP server that scans Salesforce Agentforce metadata for security vulnerabilities using 61+ SAST rules, integrating into AI coding workflows to guard against OWASP LLM top 10 risks.

Open-source privacy and approval gateway between AI assistants and your business systems (MCP): human approval, local PII checks and audit for Gmail, Drive, Slack, Salesforce, Jira and more.

Enables AI agents to reach enterprise apps such as Jira, Microsoft 365, Salesforce, FedEx and Dell TechDirect, or your own REST APIs, through a single self-hosted MCP endpoint. Each agent gets its own key with per-app, per-value grants and a confirmation step for deletes, so calls are scoped and audited without exposing app credentials.

Permission gateway that hands an AI agent a scoped MCP endpoint instead of an OAuth token: connect 27 services (Gmail, Google Calendar/Drive/Ads/Search Console, Slack, Notion, GitHub, Jira, Salesforce, HubSpot, Stripe, LinkedIn, X, Meta Ads and more), grant per-action permissions finer than native OAuth scopes, audit every call and revoke a key in one click. Self-hostable, MIT.

Enables AI agents to query, count, and run Elasticsearch searches over security events across an MSP's customers' Microsoft 365, Google Workspace, Salesforce, and Dropbox tenants, and to list customers, users, devices, billing periods, and scheduled reports, with explicit write operations for managing customers, whitelists, reports, and branding.

Ledgent is a secure agentic integration layer that exposes Salesforce and billing operations as MCP tools. It enforces action-level authorization, idempotency, PII tokenization, and full audit logging, enabling AI agents to safely perform writes with human approval for high-risk actions.