AI and agents MCP servers
MCP servers that give AI agents memory, reasoning tools, models and other agents to work with.
This directory lists MCP servers, not LicenseSaaS listings. For software available for licensing and white-labeling, browse the marketplace.
14499 servers
Prompt Injection Scanner
Scans RAG content/scraped pages for indirect prompt injection
Runs locally · AI and agents · Developer tools
Prompt Injection Scanner
Scans RAG content/scraped pages for indirect prompt injection
Runs locally · AI and agents · Developer tools
Prompt Optimizer
Optimize prompts and generate agent SOPs and skill packages with the Prompt Optimizer cloud API.
Runs locally · AI and agents · Developer tools
Prompt Time
Claude Desktop reminders for Windows. Survives MSIX boundary; persists across restarts. Zero deps.
Runs locally · Developer tools · AI and agents
Prompt To Asset
Generate app icons, favicons, OG images, and logos by routing across 30+ image models.
Runs locally · Developer tools · AI and agents
prompt-protection
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Runs locally · AI and agents · Developer tools
PromptBranch
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
Runs locally · Developer tools · AI and agents
Promptbudget Mcp
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
Runs locally · AI and agents · Developer tools
Promptheus
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
Runs locally · AI and agents · Developer tools
Promptibus MCP
Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.
Runs locally · AI and agents
Promptlike Mcp
Your PromptLikeEngineer prompt library as MCP tools, slash prompts and resources. No delete tool.
Runs locally · AI and agents · Developer tools
Promptlint MCP
Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.
Runs locally · Developer tools · AI and agents
Promptpack
Check a prompt-template pack from supplied templates: variables, versions, test renders.
Runs locally · Developer tools · AI and agents
Promptrejectormcp
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Runs locally · Security · AI and agents
PromptSpeak Governance
Pre-execution governance for AI agents. Validates tool calls before they execute.
Runs locally · Developer tools · AI and agents
Prompyai
Scores your prompts against your real codebase — context-aware prompt intelligence
Runs locally · AI and agents · Developer tools
Proof
Govern your AI coding agent: frame the work, review the changes, keep a signed decision record.
Runs locally · Developer tools · AI and agents
Proof Layer
Signed, hash-chained provenance receipts for AI agent actions.
Runs locally · Developer tools · AI and agents
Proof of Work
Post, vote and back claims with evidence on Proof of Work, the front page for people and AI agents.
Runs locally · Developer tools · AI and agents
ProofFlow
Audit infrastructure for AI coding agents with evidence-backed review and policy gates.
Runs locally · Developer tools · AI and agents
ProofGraph (Antigravity MCP)
Evidence-first entity and knowledge graph MCP server for AI agents to verify claims.
Runs locally · Developer tools · AI and agents
ProofSlip
Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects
Runs locally · AI and agents
Protect Mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
Runs locally · AI and agents
Protect Mcp
Signed receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.
Runs locally · Developer tools · AI and agents · Deprecated
protect-context
Agent guardrails: contract, evidence ledger, loop brake, diff-scope warnings, durable journal.
Runs locally · Legal · Developer tools
PROTEUS terminal
Windows terminal sessions for agents: spawn, type, wait without polling, lean reads, screenshots.
Runs locally · Developer tools · AI and agents
Proven
Judge AI-written Python: no invented packages or calls, no facts from memory, verified LLM output.
Runs locally · AI and agents · Developer tools
Provena Agent Memory
Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.
Runs locally · AI and agents · Developer tools
Provenance Mcp
Wash-traffic risk checks for Algorand x402 endpoints before your agent trusts or pays them.
Runs locally · Developer tools · AI and agents
Provenonce
Cryptographic identity, SIGIL naming, heartbeat, and passports for AI agents.
Runs locally · Developer tools · Security
Source: the official MCP Registry (registry.modelcontextprotocol.io). Entries are published by their owners and not checked by LicenseSaaS.