Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
cMCP (AgenTrust)
Confidential MCP gateway: checks every tool call against Cedar policies, optionally inside a hardware TEE the agent and host admin cannot tamper with, and issues a signed receipt (TRACE claim) per session.
cmcp.agentrust-io.com/Active
v0.7.1 released 2026-10-20; repo pushed 2026-10-23; 'Developer Preview' since 2026-06-23. (checked 2026-10-25)
In Agent guardrails
Where it stands apart
- How is it mainly sustained? company or startup with a free product (no revenue yet) (10% of 20 others)
- Which shared standard or format does it mainly build on? Model Context Protocol (MCP) (19% of 21 others)
- What is the main thing it protects? outside systems and data (APIs, databases, money, private records) (19% of 21 others)
- Does it keep a record of agent actions? yes, tamper-evident (signed or hash-chained) (10% of 20 others)
What it shares with most of the community
- Is it actively maintained? active (81% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (67% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (76% of 21 others)
- Do you need an account to use it? no account (67% of 21 others)
- Who is it for? developers (90% of 21 others)
- What mainly decides whether an action is allowed? rules, policy, or boundaries written in advance (57% of 21 others)
- Which agents does it work with? any agent or process (not limited to a named list) (71% of 21 others)
- In the default setup, where does the agent's work actually execute? directly on the host machine, as usual (52% of 21 others)
- What is it mainly for? adding checkpoints, review, or evidence (52% of 21 others)
- Is enforcement kept out of the agent's reach? yes, enforced in code or infrastructure the agent cannot change (95% of 21 others)
Not documented
The public sources we read don't say:
- If the guard itself breaks, is missing, or cannot decide, what happens by default?
- Does it control the agent's outbound network access?
Nearest neighbors
- Conduct 80% of 15 shared answers match
- Noisegate 80% of 15 shared answers match
- Vultrino 80% of 15 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) MIT | source 2026-10-25 |
| How is it mainly sustained? | stands apart company or startup with a free product (no revenue yet) AgenTrust publishes free open specs and tools; no pricing found. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes Software mode anywhere; hardware mode needs TEE-capable machines. | source 2026-10-25 |
| Do you need an account to use it? | no account pip install cmcp-runtime and run locally in software mode; no signup. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart Model Context Protocol (MCP) An MCP gateway (Cedar policies on top). | source 2026-10-26 |
| Where does it mainly step in? | at the tool-call, MCP, or API layer (proxy or gateway) | source 2026-10-25 |
| What mainly decides whether an action is allowed? | rules, policy, or boundaries written in advance Cedar policy bundles. | source 2026-10-25 |
| If the guard itself breaks, is missing, or cannot decide, what happens by default? | Not documented Default enforcement_mode is 'enforcing'; error behaviour not stated. | source 2026-10-25 |
| Which agents does it work with? | any agent or process (not limited to a named list) | source 2026-10-25 |
| In the default setup, where does the agent's work actually execute? | directly on the host machine, as usual | source 2026-10-25 |
| What is the main thing it protects? | stands apart outside systems and data (APIs, databases, money, private records) Tool access to databases, CRMs, email and internal APIs. | source 2026-10-25 |
| Does it keep a record of agent actions? | stands apart yes, tamper-evident (signed or hash-chained) Signed receipts, hardware-attested in TEE mode. | source 2026-10-25 |
| Does it control the agent's outbound network access? | Not documented | source 2026-10-25 |
| What is it mainly for? | adding checkpoints, review, or evidence | source 2026-10-25 |
| Is enforcement kept out of the agent's reach? | yes, enforced in code or infrastructure the agent cannot change | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/agentrust-io/cmcp · read 2026-10-25
- Web page · agentrust-io.com · read 2026-10-25
- Web page · cmcp.agentrust-io.com/ · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.