ZBS Index What actually exists in applied AI, with the source next to it

mcp server

chp

Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer.

Description as published by the maintainer. Source

  • version 0.8.0
  • active

active — Most recent push to the repository was 2026-07-20.

What this server can do

9 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

define(term)
Define a CHP primitive. Pass a term, or omit to list the glossary.
explain(topic)
Learn what CHP is and how it works. Pass a topic, or omit to list topics. Topics: what-is-chp, evidence-model, why-a-protocol, governance, agentic-web, evidence-vs-telemetry, chp-vs-mcp, conformance.
faq(query)
Common questions about CHP. Pass a query to filter, or omit for all.
get_capability(id)
Resolve a capability id to its descriptor. Required: id.
get_example(name)
Get a runnable example. Pass a name, or omit to list examples. Names: hooks-install, inspect-session, minimal, agentic, rag, safety, persistence, evidence-output.
how_to_adopt
Get the steps to start using CHP (begin with agents).
list_adapters(category)
Browse the open adapter ecosystem, optionally by category.
list_capabilities(category)
List the capabilities the open CHP adapter ecosystem declares, optionally by category.
search(query)
Search CHP concepts, glossary, FAQs, and the capability catalog. Required: query.

Last successful function declaration observed on . Source: https://capabilityhostprotocol.com/api/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://capabilityhostprotocol.com/api/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 1 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-07-20 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 23 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 0.8.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-06-24 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-06-24 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub
mcp tools declared 9 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe capabilityhostprotocol.com
mcp endpoint status ok The server listed 9 functions when asked. as of probe capabilityhostprotocol.com

Where to get it

Related, by what their authors tagged them

  • ai.marchward/mcp-server — last commit 2026-07-01, shares tool-calling
    Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
  • com.thingctx/thingctx — last commit 2026-08-04, shares tool-calling
    Drive devices and APIs from their W3C Thing Description. You gate every operation.
  • Froglet — last commit 2026-07-05, shares protocol
    Run local Froglet verifiable compute, signed receipts, settlement, and service publication.
  • io.github.Bayway/janusmcp — last commit 2026-08-04, shares tool-calling
    Multi-account tool broker for AI agents — CLI and MCP.
  • Agent^Rider — last commit 2026-08-04, shares protocol
    Signed agent identity, trust scoring, credit economy, and social layer for AI agents.
  • io.github.codyz123/schelling-protocol — last commit 2026-03-28, shares protocol
    Universal coordination protocol for AI agents. Discovery, matching, and negotiation.
  • io.github.containers/kubernetes-mcp-server — last commit 2026-08-06, shares protocol
    A Model Context Protocol (MCP) server for Kubernetes and OpenShift
  • io.github.dappros/ethora-mcp-cli — last commit 2026-08-01, shares tool-calling
    MCP server for the Ethora chat & messaging platform: chat ops, AI agents, RAG, automation.
  • io.github.dappros/ethora-mcp-server — last commit 2026-08-01, shares tool-calling
    MCP server for the Ethora chat & messaging platform: chat ops, AI agents, RAG, automation.
  • io.github.DIDA-AI/hotelbooking-ai — last commit 2026-08-04, shares tool-calling
    Hotel Booking MCP Server (Global/AI Edition)

These share tags the maintainers applied themselves, such as tool-calling, protocol. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

Also from capabilityhostprotocol

How the author describes it

Topics the maintainer set on GitHub: agents, evidence, governance, llm, observability, protocol, python, replay, tool-calling.

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. capabilityhostprotocol/chp-core on GitHub — GitHub, observed , trust tier 3.
  2. Tools declared by the MCP server at https://capabilityhostprotocol.com/api/mcp — capabilityhostprotocol.com, observed , trust tier 1.
  3. Official MCP Registry — Model Context Protocol, observed , trust tier 1.