Editing
AgentFinger
Jump to navigation
Jump to search
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
{{Infobox protocol | name = AgentFinger | developer = [[secondtruthLabs]] | status = Draft | first_published = 2025 | latest_version = 0.3 | based_on = [[Common Text-based Response Protocol|CTRP]] | transport = [[wp:Transmission Control Protocol|TCP]] | default_port = 7922 (TCP), 7923 (TLS) | encoding = [[wp:UTF-8|UTF-8]] | license = [[wp:Public domain|Public Domain]] }} '''AgentFinger''' is an application protocol for discovering and retrieving structured information about users, AI agents, organizations, and [[wp:Model_Context_Protocol|MCP]] servers. Built on [[Common Text-based Response Protocol|CTRP]], it is specifically optimized for consumption by [[wp:Large language model|Large Language Models]]. == Overview == AgentFinger extends the classic [[wp:Finger protocol|Finger protocol]] concept for the AI agent ecosystem. It provides a standardized way for agents to discover information about other agents, their capabilities, and their organizational context. === Design philosophy === * '''Agent-first design''' β Optimized for LLM consumption * '''Markdown-native''' β Semantic readability without complex parsing * '''Distributed architecture''' β No central registry required * '''Reasonable security''' β Designed for trusted networks == Technical specification == === Entity types === AgentFinger supports four entity types: {| class="wikitable" |- ! Type !! Prefix !! Description |- | User || <code>user:</code> || Human users and their profiles |- | Organization || <code>org:</code> || Organizations and projects |- | Agent || <code>agent:</code> || AI agents and their capabilities |- | MCP Server || <code>mcp:</code> || [[wp:Model_Context_Protocol|MCP]] server capabilities |} === Query format === Queries follow a URI-like structure: {{Code example | language = text | caption = Query format | code = <type>:<id>@<host>[/<path>][?<query>] }} Examples: {{Code example | language = text | caption = Example queries | code = user:alice@example.com agent:assistant@ai.example.com org:research@labs.example.com/projects mcp:tools@mcp.example.com?format=json }} Type prefixes are mandatory to avoid ambiguity. === Response format === Responses use [[wp:Markdown|Markdown]] with [[wp:YAML|YAML]] frontmatter: {{Code example | language = markdown | caption = Example response | code = --- type: agent id: assistant name: Research Assistant capabilities: - text-generation - code-analysis --- # Research Assistant An AI agent specialized in academic research support. ## Capabilities - Literature review - Citation management - Summary generation }} === Path-based resources === Entities can expose hierarchical resources: {{Code example | language = text | caption = Path examples | code = org:stlabs@example.com/projects org:stlabs@example.com/projects/agentfinger agent:helper@example.com/tools }} === Query parameters === {| class="wikitable" |- ! Parameter !! Values !! Description |- | <code>format</code> || <code>md</code>, <code>json</code>, <code>yaml</code> || Response format |- | <code>section</code> || Section name || Return only specified section |} == Security considerations == AgentFinger is designed for trusted network environments. Implementations should consider: * Access control lists for sensitive information * Rate limiting to prevent abuse * TLS encryption for sensitive data * Authentication for write operations (if supported) == Discovery == AgentFinger services can be discovered using [[Trivial Service Discovery Protocol|TSDP]]: {{Code example | language = text | caption = TSDP discovery | code = DISCOVER agentfinger * * }} == Implementations == === Reference implementation === The reference server implementation is written in [[wp:Go (programming language)|Go]]. == Use cases == * Agent-to-agent communication and discovery * Identity and context discovery for LLM personalization * Organization and project documentation * MCP server capability advertisement == See also == * [[Common Text-based Response Protocol]] * [[Trivial Service Discovery Protocol]] * [[wp:Model_Context_Protocol]] * [[wp:Finger protocol]] == References == {{Reflist}} == External links == * [https://github.com/secondtruth/agentfinger AgentFinger Repository] [[Category:Communication Protocols]] [[Category:Application Protocols]] [[Category:Identity Protocols]] [[Category:AI Agent Architecture]] {{stLabs protocol}}
Summary:
Please note that all contributions to secondtruthLabs Wiki may be edited, altered, or removed by other contributors. If you do not want your writing to be edited mercilessly, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource (see
secondtruthLabs Wiki:Copyrights
for details).
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)
Templates used on this page:
Template:Code example
(
edit
)
Template:Infobox protocol
(
edit
)
Template:Reflist
(
edit
)
Template:StLabs protocol
(
edit
)
Navigation menu
Personal tools
Not logged in
Talk
Contributions
Create account
Log in
Namespaces
Page
Discussion
English
Views
Read
Edit
Edit source
View history
More
Search
Navigation
Main page
Recent changes
Random page
Help about MediaWiki
Tools
What links here
Related changes
Special pages
Page information