
Chp
io.github.capabilityhostprotocolPublished by GitHub account capabilityhostprotocolv0.8.0Updated Oct 25, 2026
Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer.
Overview
A remote endpoint for the Capability Host Protocol, an open evidence layer for recording and replaying what agents, tools and systems did and what governed them
- What you can do
- Learn and adopt the Capability Host Protocol through a hosted endpoint at capabilityhostprotocol.com, which the manifest lists with no tools of its own, so the assistant mainly gets protocol context rather than callable actions. The protocol itself defines capability and host descriptors, invocation envelopes, correlation context, structured execution evidence, outcome, error and denial semantics, and replay queries. Evidence events are hash-chained and stored locally in an SQLite store, and replay works by correlation ID. A policy can be evaluated against a past run to show what it would have denied. Reference implementations exist in Python and TypeScript, with an experimental MCP bridge.
- When to use it
- Worth adding when you want to understand or adopt CHP as a governed, tamper-evident record of agent and tool execution, or to compare it with MCP and OpenTelemetry. It is not a general-purpose tool server, so it adds little if you only need callable tools.
- Requirements
- A remote streamable HTTP endpoint at capabilityhostprotocol.com; the manifest declares no authentication, environment variables or headers. Local use of the protocol needs Python (pip install chp-core) or Node.js for the TypeScript SDK, and writes evidence to a local SQLite file under the user's home directory.
Installation
In SourceWeft
- Open Chp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.capabilityhostprotocol%2Fchp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"chp": {
"type": "http",
"url": "https://capabilityhostprotocol.com/api/mcp"
}
}
}README
Capability Host Protocol
[PyPI] [Python] [npm] [License] [Docs]
CHP is the open protocol for declaring, governing, and proving what agents, tools, and systems do — the single signed plane where a human approval, an agent's action, and a system call become the same governed, tamper-evident, replayable event.
The hook is simple:
See what your agents and tools actually did — and what governed it.
Try it in two minutes
Your coding agent reads files, runs commands, calls tools. This puts a governed boundary at the point of action — no application code changes:
Use your agent normally, then look at what it did:
Every tool call is a typed evidence event, hash-chained and stored locally in ~/.chp/evidence.sqlite. A denial is a first-class event with a reason code — not a swallowed exception — and the chain is tamper-evident, so someone who did not run the agent can still tell whether the record is intact.
Prefer to drive the protocol directly? chp serve-demo starts a governed host and prints a copy-pasteable first invocation.
Full guide: docs/quickstart.md · why it exists: docs/why-chp.md · docs site: docs.capabilityhostprotocol.com
What you get back
Replay is by correlation ID, and the record answers more than "what happened" — from examples/agent-operations-demo/:
You can also ask what a policy would have done to a run that already happened:
Why a protocol, not a library
CHP is not another agent framework, tool protocol, or workflow engine. It is the governed evidence plane at the capability boundary: what ran and what governed it (policy, risk tier, safety checks, human approval, autonomy budgets, denial) emit onto one signed, correlated record. Observability tools split execution across separate, optional, unsigned signals and carry no governance; CHP unifies both and proves them.
Status: CHP is a pre-1.0 release candidate (v0.9.3) — a frozen, additive wire surface backed by two independent implementations (Python + TypeScript) that pass conformance. chp-core ships on PyPI.
What CHP Defines
- Capability descriptors
- Host descriptors
- Invocation envelopes
- Correlation context
- Structured execution evidence
- Outcome, error, and denial semantics
- Replay queries and results
- Replay by correlation ID
- Minimal conformance requirements
Install
chp host verify smoke-tests the install in under a second and reports whether input-schema validation is enforced.
From this checkout: python -m pip install -e packages/python.
Minimal Capability
The host emits execution_started and execution_completed evidence for the invocation. If execution fails, it emits execution_failed. If the host denies invocation, it emits execution_denied.
Repository Map
spec/README.md: the specification index — core (v0.1), governance vocabulary, invocation pipeline, HTTP binding, evidence integrity + anchors (v0.2), reserved names, test vectors, changelog, proposal processschemas/: JSON Schemas for protocol objectspackages/python/chp_core/: reference host (Python)packages/chp-sdk/+packages/chp-host-ts/: the second implementation (TypeScript)examples/capability-host-endpoint-demo/: HTTP-served host demoexamples/agent-operations-demo/: agent/tool observability demoexamples/codex-self-observation-demo/: Codex dogfooding demoexamples/mcp-bridge-demo/: experimental MCP-style bridge prototypeconformance/: conformance runnerdocs/quickstart.md: install, first run, serving, meshdocs/why-chp.md: the problem and the thesisdocs/adapter-authoring.md: writing your own capability adapterdocs/production-runbook.md: operations, backup/restore, key compromisedocs/comparisons/chp-vs-mcp.md: precise MCP comparisondocs/comparisons/chp-and-opentelemetry.md: OpenTelemetry alignment notedocs/comparisons/landscape.md: adjacent framework comparisondocs/security/threat-model-v0.1.md: v0.1 threat model
Production Posture
The reference implementation is hardened for production operation: WAL
multi-writer safety with hot backup (chp store backup --verify), SIGTERM
drain (in-flight work completes before exit), a fail-loud auth flag
(CHP_HOST_REQUIRE_AUTH=1), scheduled retention, and operator metrics (store
size, witness-loop liveness, revocation counts, internal errors). Operations,
backup/restore, rolling upgrades, and the key-compromise runbook:
docs/production-runbook.md. Vulnerability
reporting: SECURITY.md.
CHP vs MCP
MCP exposes tools and context to AI applications. CHP governs and evidences execution of capabilities.
They fit together. MCP can be a source of capability invocation, and CHP adds correlation, replay, evidence, denial semantics, and governance at the execution boundary.
Read more: docs/comparisons/chp-vs-mcp.md.
Contributing
Read CONTRIBUTING.md first. One thing to know before you open a pull request: this repository is a generated mirror of a private development repository. CI rejects pull requests that touch packages/, docs/, spec/, schemas/, or examples/ from a branch that is not sync/*, so a code PR against those paths will fail by construction no matter how good it is.
That is not a brush-off — it is the publishing model, and we would rather say so up front than let you find out from a red check. Issues, spec proposals, comparisons, and discussion are the highest-bandwidth way in today; open an issue and we will route the change through the internal flow with attribution.
Open Source Boundary
Open source should include local visibility:
- spec and schemas
- local host
- SDK primitives
- conformance
- local replay
- agent observability wrapper
- experimental MCP bridge prototype
Commercial value can remain around production trust:
- hosted capability graph
- multi-host trace stitching
- retention
- team workspaces
- advanced explanation
- invariant libraries
- assurance derivation
- compliance exports
- enterprise identity and RBAC
Guiding rule:
Local visibility should be free. Production trust should be paid.
License
CHP is dual-licensed by asset:
- Code (
packages/,conformance/,examples/,scripts/): Apache License 2.0 — seeLICENSE. - Specification, schemas & docs (
spec/,schemas/,docs/): Creative Commons Attribution 4.0 (CC BY 4.0) — seeLICENSE-DOCS. Implementing the specification is additionally covered by a royalty-free patent grant — seePATENTS. - Trademarks: "CHP" and "CHP-Certified" — see
TRADEMARK.md.
Contributions are accepted under the Contributor License Agreement; see CONTRIBUTING.md.
Copyright © 2026 Project Auxo, Inc. See NOTICE.
Source: README.md at commit 6ffb84a
Tools
0Version history
1- v0.8.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts