Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pantheon-mcp list agents in the tech category"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A collection of AI agents for various tasks.
Welcome to the agents repository! This project contains various AI agent definitions. The definitions can be used by any agentic system that supports markdown.
An MCP (Model Context Protocol) server that delivers AI agent instructions on demand from this repository's collection of 42+ specialized agents.
{
"mcpServers": {
"pantheon-mcp": {
"type": "stdio",
"command": "npx",
"args": ["-y", "pantheon-mcp"],
"env": {}
}
}
}Related MCP server: Awesome Agent Skills MCP Server
The server exposes 3 MCP tools:
list_agentsList all available agents, optionally filtered by category.
{
"name": "list_agents",
"arguments": {
"category": "tech" // optional: business, growth, product, tech
}
}get_agentGet detailed information about a specific agent by name.
{
"name": "get_agent",
"arguments": {
"name": "react-frontend-dev"
}
}search_agentsSearch agents by keywords in name, description, or instructions.
{
"name": "search_agents",
"arguments": {
"keywords": "react",
"category": "tech" // optional filter
}
}business (6 agents): business-analyst, cfo-financial-analyzer, compliance-officer, financial-analyst, sales-strategist, startup-mentor
growth (5 agents): conversion-optimizer, growth-marketer, idea-visionary, marketing-copywriter, marketing-strategist
product (3 agents): product-designer, product-manager, product-strategist
tech (28 agents): accessibility-auditor, ai-prompt-engineer, api-designer, aws-cloud-architect, code-reviewer, react-frontend-dev, and many more...
To install globally:
npm install -g pantheon-mcp
npx pantheon-mcpnpm install
npm run build
npm run devBuilt with ❤️ and AI
Get a specific agent by name
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The name of the agent to retrieve |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It only states the basic function, without mentioning whether the operation is read-only, what happens if the agent does not exist, or any other behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded and contains no unnecessary words. It is highly concise and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should clarify what is returned. It does not mention the return value (e.g., the agent object). For a simple get operation, the description is adequate but lacks completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter 'name', and the description mirrors the schema's description. The description adds no additional meaning beyond what the schema already provides, resulting in a baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'specific agent', and specifies the filter 'by name'. It distinguishes itself from sibling tools 'list_agents' and 'search_agents' by implying this tool retrieves a single agent by an exact name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not explain when to use this tool versus list_agents or search_agents, nor does it mention any prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available AI agents with their metadata
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Filter agents by category |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It only states 'list all' without mentioning pagination, rate limits, or read-only nature. For a listing tool, this lacks transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that conveys the tool's purpose without superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (one optional parameter, no output schema), the description is mostly complete. It misses details on return format, but that is acceptable for a simple list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema coverage is 100%, and the description adds no extra meaning beyond the schema's parameter description of 'Filter agents by category'. Baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'list', the resource 'AI agents', and the included metadata, distinguishing it from siblings like 'get_agent' (single agent) and 'search_agents' (search functionality).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving all agents, but does not explicitly contrast with siblings or provide when-not-to-use guidance. However, the purpose is clear enough for basic selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search agents by keywords in name, description, or content
| Name | Required | Description | Default |
|---|---|---|---|
| keywords | Yes | Keywords to search for | |
| category | No | Filter by category |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as pagination, sorting, case sensitivity, or response format. The description only states the basic function, leaving significant gaps for the agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the essential purpose without any superfluous words. It is well-structured for quick comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks details about output format, pagination, or other behaviors typical of a search tool. Given no output schema and no annotations, the description should provide more context to be complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers both parameters with descriptions, achieving 100% coverage. The description adds value by specifying that keywords are searched in 'name, description, or content', which provides context beyond the schema. The 'category' parameter is already described in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'search' and the resource 'agents', and specifies the fields being searched ('name, description, or content'). This distinguishes it from siblings like 'get_agent' (single retrieval) and 'list_agents' (listing without search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for keyword-based searching but does not explicitly state when to use this tool versus alternatives. No exclusions or context about when not to use it are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool targets a distinct operation: retrieving a specific agent by name, listing all agents, and searching by keywords. No overlap in purpose.
All tool names follow a consistent verb_noun pattern with snake_case: get_agent, list_agents, search_agents. Perfectly uniform.
Three tools cover the essential query operations for agents. Slightly low count, but well-scoped for a read-only agent directory.
Covers retrieval and search but lacks creation, update, or deletion tools. May be intentional for a read-only surface, but from a general perspective, CRUD operations are missing.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI Agent Source Registry. 288K+ curated sources for agentic search and discovery.
Directory of APIs, merchants, and tools AI agents can actually use.
One place to build, share, and govern the skills and tools your AI agents use at work.
Curated operational knowledge for AI agents. 2 tools. Paid.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/valado/pantheon-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
