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., "@Agent Directory MCP Server search for image generation services"
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.
Agent-to-Agent service directory — a Yellow Pages for AI agents. Discover, register, and rate AI services.
AI agents need to find other agents/services to collaborate with. There's no standardized way for agents to discover what services are available and which are trustworthy.
Related MCP server: Moltjiji
Register Services — Add your agent/service to the directory
Search & Discover — Find services by capability, category, or keyword
Ratings & Reviews — Community-driven quality signals
Categories — Organized by domain (finance, weather, data, etc.)
MCP Config — Services include their MCP configuration for instant setup
pip install agent-directory-mcp-server{
"mcpServers": {
"directory": {
"command": "uvx",
"args": ["agent-directory-mcp-server"]
}
}
}Tool | Description |
| Register a service in the directory |
| Search for services by keyword/category |
| Get details of a specific service |
| Rate a service (1-5 stars) |
| List all service categories |
| Show highest-rated services |
| Directory statistics |
The more services registered, the more useful the directory becomes. The more agents use it for discovery, the more valuable it is to register. This creates a flywheel effect that makes early adoption especially valuable.
Category | Servers |
đź”— Blockchain | |
🌍 Data | Weather · Germany · Agriculture · Space · Aviation · EU Companies |
đź”’ Security | |
🤖 Agent Infra | Memory · Directory · Hub · Reputation |
🔬 Research | Academic · LLM Benchmark · Legal |
→ Full catalog (40+ servers)
MIT
Verzeichnis-Statistiken abrufen.
Gesamtzahl Services, Kategorien, Bewertungen.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It implies a read-only operation ('abrufen') and lists output contents, but does not disclose any additional behavioral traits such as rate limits, data freshness, or potential side effects. The description is minimally adequate.
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 extremely concise, consisting of two short lines. It front-loads the purpose and lists outputs without any superfluous words. Every part earns its place.
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?
For a parameterless tool with no output schema, the description adequately covers what the tool does and what it returns (total numbers of services, categories, ratings). It is complete enough for its simplicity, though it could mention that results are aggregated.
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 tool has zero parameters, so the baseline is 4. The description does not need to add parameter details, and it correctly reflects that no input is required.
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 'abrufen' (retrieve) and the resource 'directory statistics', specifying it returns total counts of services, categories, and ratings. While it distinguishes itself from sibling tools like get_service and list_categories by implying aggregate data, it does not explicitly contrast with them.
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 provides no guidance on when to use this tool versus alternatives like list_categories or top_services. It only states what it does, leaving the agent to infer the use case without explicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Details eines bestimmten Service abrufen.
Args: name: Name des Services
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description bears full responsibility for behavioral disclosure. It fails to mention what is returned (e.g., fields, format) or any side effects, leaving the agent with incomplete information.
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 short and includes an Args section, which is acceptable, but it could be more structured with a return description. It is concise but under-informative.
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?
For a simple tool with one parameter and no output schema, the description is minimally adequate. However, it lacks information about return values, making it somewhat incomplete for an agent to fully understand the tool's behavior.
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 description coverage is 0%, but the description explains the single parameter 'name' as 'Name des Services', adding meaning beyond the schema's title and type.
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 ('abrufen' i.e., retrieve) and the resource ('Details eines bestimmten Service'), making it distinct from sibling tools like 'search_services' or 'list_categories'.
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 guidance is provided on when to use this tool versus alternatives (e.g., search_services, top_services). The description offers no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Alle Service-Kategorien auflisten.
Zeigt welche Kategorien es gibt und wie viele Services jeweils registriert sind.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool returns a list of categories and their service counts, but it lacks details about sorting, pagination, or whether only categories with at least one service are included. Given no annotations, the description carries the full burden, and these missing behavioral characteristics reduce 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 two short sentences with no fluff. The first sentence immediately states the core purpose, and the second adds a key detail (service counts). Every word adds value.
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?
For a parameterless listing tool with no output schema, the description adequately covers what the tool does and what output to expect (categories with counts). No further details are necessary for competent use.
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?
There are no parameters, so the input schema is trivially covered. The description does not need to add parameter information. It correctly leaves the schema to speak for itself.
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 that the tool lists all service categories and shows the number of services registered in each. The verb 'auflisten' combined with the resource 'Service-Kategorien' makes the purpose explicit and distinct from sibling tools that focus on individual services or statistics.
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 that this tool is for retrieving category-level aggregation data, but it does not explicitly state when to use this tool over siblings like 'get_service' or 'search_services'. A sentence contrasting with other tools or indicating prerequisites could improve clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Einen Service bewerten (1-5 Sterne).
Hilft anderen Agents, gute Services zu finden.
Args: service_name: Name des zu bewertenden Services rating: Bewertung 1-5 (5 = beste) review: Optionaler Bewertungstext
| Name | Required | Description | Default |
|---|---|---|---|
| service_name | Yes | ||
| rating | Yes | ||
| review | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only states the action (rate) but does not mention side effects (e.g., whether previous ratings are overwritten), required permissions, or idempotency. This is insufficient for a mutation tool.
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 concise with a clear 'Args' section. The second sentence is not critical but does not detract. It is well-structured for quick parsing.
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 lack of annotations and output schema, the description is incomplete. It does not explain what the tool returns (e.g., success message or error) or provide behavioral context beyond the basic action.
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?
While schema coverage is 0%, the description provides clear semantics: service_name is the name of the service, rating is 1-5 (5 best), review is optional. This adds meaning beyond the schema's type annotations.
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 'Rate a service (1-5 stars)', specifying the verb and resource. It is distinct from sibling tools like 'get_service' (read) and 'register_service' (create). However, the additional sentence about helping agents find good services adds slight ambiguity.
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 explicit guidance on when to use this tool versus alternatives. It does not mention exclusions or prerequisites. The purpose is implied, but lacking direct context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Einen AI-Agent-Service im Verzeichnis registrieren.
Args: name: Eindeutiger Service-Name description: Was der Service macht category: Kategorie (z.B. "finance", "weather", "data") capabilities: Liste der Fähigkeiten endpoint: URL oder MCP-Endpoint mcp_config: MCP Server Konfiguration (JSON) author: Autor/Entwickler tags: Tags für bessere Auffindbarkeit
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| description | Yes | ||
| category | Yes | ||
| capabilities | No | ||
| endpoint | No | ||
| mcp_config | No | ||
| author | No | ||
| tags | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It does not mention side effects (e.g., overwriting existing services), required permissions, or rate limits. The description is purely functional with no behavioral context.
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 plus a bullet list of parameters, which is efficient and easy to scan. It is concise but lacks a structured format; the parameter list is clear.
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 tool has 8 parameters and no output schema, the description covers parameter meanings but omits important context like return behavior, error handling, or duplicate handling. It is minimally complete for simple registration but lacks depth.
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?
Although the schema has 0% description coverage, the description provides German translations and brief explanations for all 8 parameters (e.g., 'capabilities: Liste der Fähigkeiten'). This adds meaning beyond the bare JSON schema titles, though descriptions are minimal.
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 tool's purpose: 'Einen AI-Agent-Service im Verzeichnis registrieren' (register an AI agent service in the directory). The verb 'register' and resource 'AI agent service' are specific and distinguishable from sibling tools like get_service or search_services.
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 provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or when not to use it. It only describes the action without contextual usage advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Nach AI-Agent-Services suchen.
Durchsucht das Verzeichnis nach Services die bestimmte Fähigkeiten oder Funktionen bieten.
Args: query: Suchbegriff (durchsucht Name, Beschreibung, Fähigkeiten) category: Optional — nur in dieser Kategorie suchen tags: Optional — nur Services mit diesen Tags limit: Maximale Ergebnisse (Standard: 10)
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| category | No | ||
| tags | No | ||
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool searches the directory and lists filter parameters, but it does not disclose whether the operation is read-only, if authentication is needed, or what the return format is. Behavioral traits like pagination, ordering, or empty result handling are absent.
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 concise: a title, a one-sentence summary, then a clear list of parameter explanations. No wasted words, and the structure is 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?
For a search tool with 4 parameters and no output schema or annotations, the description covers the basic purpose and parameters. However, it is missing key details like return format (what does the result list contain?), default ordering, or whether search is fuzzy/exact. These gaps limit completeness to a 3.
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?
With 0% schema description coverage, the description adds essential meaning: query searches name/description/capabilities, category is an optional filter, tags is optional, and limit sets max results (default 10). This compensates well for the bare schema, earning a 4.
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 'Nach AI-Agent-Services suchen' and explains that it searches the directory for services with specific capabilities. The verb 'search' and resource 'services' are explicit, and the context of sibling tools (e.g., get_service, list_categories) implies its role as a broader search tool. However, it does not explicitly differentiate from siblings, so it gets a 4.
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: when you want to find services by query, category, or tags. But it does not explicitly state when to use this tool versus alternatives like get_service or top_services, nor does it mention when not to use it. No exclusion criteria or prerequisites are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Top-bewertete Services anzeigen.
Die bestbewerteten Services im Verzeichnis.
Args: limit: Anzahl (Standard: 10)
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It only says 'die bestbewerteten Services' (the highest-rated services), but does not mention that it is a read-only operation, any side effects, authorization needs, or how the results are ordered or limited. The behavior is under-specified.
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 short and structured: a title sentence, a clarifying sentence, and an Args block. There is no unnecessary information. However, it could be more concise by avoiding the repetition of 'Services'.
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?
For a tool with no output schema and one parameter, the description should explain what the tool returns and how the limit affects output. It lacks details on the result format (list, fields, ordering). The description is minimal and leaves the agent with significant unknowns about the output.
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 description adds meaning to the 'limit' parameter beyond the schema (which only has default and type). It explains that limit is the number of results (Anzahl) with a default of 10. However, it doesn't clarify the exact semantics (e.g., max results, truncation) or any other parameter behavior. With 0% schema coverage, the description partially compensates.
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 'Top-bewertete Services anzeigen' (display top-rated services), specifying the verb and resource. It distinguishes from siblings like 'get_service' (single service) and 'search_services' (search all). However, it could be more precise about sorting and result structure.
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 guidance on when to use this tool versus alternatives like 'get_service' or 'search_services'. No conditions or exclusions provided. The description only states the basic function, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: stats, get details, list categories, rate, register, search, and top-rated. No overlap or ambiguity.
Most tools follow verb_noun pattern (get_service, list_categories, rate_service, etc.). 'directory_stats' is a noun_noun phrase but still consistent in style (lowercase, underscores). Minor deviation.
7 tools is well-scoped for an agent directory service. It covers core operations without being sparse or bloated.
Covers create (register_service), read (get_service), list/search (search_services, list_categories), and rating. Missing update_service and delete_service, which are notable gaps for full lifecycle management.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Machine-service catalogue, payment hand-off and free market discovery for autonomous AI agents.
Discover, search, invoke, and rate A2A (Agent-to-Agent) protocol agents.
Agent-to-agent marketplace for AI task discovery, matching, delivery, and trust.
Agent reputation registry: check, register, and endorse AI agents
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AiAgentKarl/agent-directory-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
