"Resources or tips for training a sales team" matching MCP servers:

Enables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.

LLM routing proxy that cuts API costs 60-90% by auto-selecting the cheapest capable model across OpenAI, Anthropic, and Google. Provides stats, config, and model comparison tools via MCP.

Boilerplate for creating a remote MCP server on Cloudflare with user login (Google/GitHub) and Stripe payment processing, enabling both free and paid MCP tools.

An MCP server that enforces safe git commits by allowing only specified files and providing fixup capabilities for earlier commits.

MCP server for team task tracking, code review, and activity monitoring via Claude Code. Assign tasks, track branch activity, review code, and get daily summaries through natural language.

MCP server that demonstrates the Resources feature by exposing static and dynamic resources, including contact data and personalized greetings, through MCP.

Shared team memory for AI coding agents with Bayesian confidence scoring and temporal decay, enabling persistent storage and retrieval of engineering patterns across sessions.

Read, search, and write Obsidian vault notes via Team Relay collaborative server. Supports shared folders, real-time sync, and AI agent access.

Enables users to leverage a team of specialized AI agent personas like Business Analysts and Product Managers through a unified interface across multiple LLM providers. It streamlines agile development workflows by providing tools for model discovery, unified prompt delivery, and role-specific decision making.

A simple MCP server implementation in TypeScript that communicates over stdio, allowing users to ask questions that end with 'yes or no' to trigger the MCP tool in Cursor.

Publishes a shared MCP endpoint where API-key users in different groups see and call only the tools their policies permit, mixing remote upstream tools with local ones. Tool discovery and execution are both filtered, hidden-tool calls are denied before their handlers run, and every action is tagged with subject and group in structured JSON logs.

Provides a local-first memory layer for coding agents, storing principles, rules, and corrections on-device and surfacing them at the moments they apply so agents act on the intended outcomes without sending data to the cloud.

Enables grouping Conventional Commit subjects into Markdown release-note sections, including breaking changes, and scanning project files for TODO/FIXME/HACK/XXX comments with file:line while respecting project boundaries and result limits.

Enables comprehensive GitHub project management automation including creating/managing issues, updating project boards, assigning team members, and analyzing repository activity across organizations through OAuth-authenticated AI assistants.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

Provides over 1,000 creative ways to decline requests across four categories (polite, humorous, professional, and creative). The MCP server wraps a REST API to help users craft professional rejections through natural language interactions.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.