Show HN: cMCP, deny an AI agent's tool call and get a signed receipt AgenTrust launched cMCP (Confidential MCP Runtime), an open-source gateway that enforces MCP tool-call policy inside a hardware Trusted Execution Environment (TEE), at the Confidential Computing Summit on June 23, 2026. The runtime intercepts every tool call, evaluates it against a Cedar policy bundle, and emits a signed TRACE Claim for verification, with a developer preview available via `pip install cmcp-runtime`. Quick Start · Architecture · Configuration · CLI · Changelog Developer Preview- launched at the Confidential Computing Summit, June 23 2026. May have breaking changes before v1.0. See STATUS.md for exactly what ships today versus what is on the roadmap. cMCP Confidential MCP Runtime is the secure, confidential way to run MCP: an open-source gateway that enforces MCP tool-call policy inside a hardware Trusted Execution Environment TEE . Every tool call is intercepted, evaluated against a Cedar policy bundle, and enforced where the process it governs cannot reach it. Each session produces a signed TRACE Claim that a verifier checks without trusting the operator, hardware-attested when the gateway runs in a TEE and signed-only in software mode. If you are looking for a secure version of MCP, this is the AgenTrust runtime for it. TL;DR- Point your agent at the cMCP Gateway. It evaluates every tool call against a Cedar policy inside a TEE, blocks or redacts what the policy denies, and emits a tamper-evident TRACE Claim as proof. Run pip install cmcp-runtime and start in software mode with no hardware required. Your agent calls Snowflake, Salesforce, a dozen APIs. What stops it from leaking a customer's data on one of those calls? If a regulator asks, could you prove it didn't? An agent calls a tool. The policy engine says allow. The tool call goes through. None of that proves the policy engine itself was not compromised. Software-only MCP governance cannot guarantee: - The Cedar policy on disk is the one that ran. A rogue admin can swap the bundle after approval; the hash check runs inside the same OS the admin controls. - The allow/deny decision was not flipped in memory. A supply chain CVE in the evaluator runs in the same address space as the attacker. - The audit log reflects what actually happened. Any party holding the software signing key can reconstruct a valid audit chain after the fact. The control plane that governs tool calls must run where it cannot be reached by the process it governs. Hardware-attested policy enforcement for MCP tool calls. Every tool call is intercepted, evaluated against a Cedar policy bundle, and enforced by a policy engine running inside a Trusted Execution Environment TEE . The policy bundle hash is measured into the hardware attestation report before any code runs. Unlike tunnel-based connectivity solutions, the cMCP Runtime processes tool-call payloads inside the TEE. The connectivity provider sees ciphertext, not plaintext. The only thing that leaves the enclave is the signed TRACE claim. pip install cmcp-runtime Create cmcp-config.yaml : attestation: provider: auto enforcement mode: advisory advisory eases first-run tuning; the default is enforcing policy bundle path: ./policies/ catalog path: ./catalog.json Start the gateway: CMCP DEV MODE=1 cmcp start --config cmcp-config.yaml Make a tool call: curl -X POST http://localhost:8443/mcp \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"salesforce.contacts","arguments":{"query":"Acme Corp"}," cmcp":{"session id":"s1","workflow id":"demo-agent"}}}' See docs/quickstart.md /agentrust-io/cmcp/blob/main/docs/quickstart.md for the full walkthrough: Cedar policy, tool catalog, first TRACE Claim, and verification no hardware TEE required . - The agent sends every tool call to the cMCP Gateway instead of directly to MCP servers. - At startup the gateway measures the Cedar policy bundle hash into the hardware attestation report. No code runs before this measurement. - Each incoming tool call is evaluated by the Cedar policy engine running inside the TEE. The result is allow, deny, or redact. The call and its decision are appended to the hardware-sealed audit chain. - At the end of the session the gateway produces a TRACE Claim: a signed, hardware-attested artifact that records which tools ran, which policy decided each call, and the full audit chain. A verifier checks this without trusting the operator. php Agent - cMCP Runtime - Cedar Policy Engine TEE - Tool | GatewayClaim TRACE Profile +-- trace.eat profile +-- trace.runtime.platform + measurement +-- trace.policy.bundle hash +-- trace.cnf.jwk Ed25519 confirmation key +-- gateway.audit chain root/tip/length +-- signature Ed25519 over canonical JSON | Provider | Platform | Assurance | Notes | |---|---|---|---| tpm | TPM 2.0 / vTPM Azure, AWS, GCP Trusted Launch | Medium | Local TPM quote | sev-snp | AMD SEV-SNP Azure DCasv5, AWS C6a Nitro | High | AMD KDS | tdx | Intel TDX Azure DCedsv5, GCP C3 | High | Intel PCS | gpu-cc v0.2 | NVIDIA H100/H200/Blackwell CC mode | High | NVIDIA Remote Attestation Service NRAS | opaque opt-in | OPAQUE Confidential Runtime | n/a not yet implemented | Placeholder: excluded from auto-detect; selecting it explicitly raises a not-implemented error | Provider auto-detect probe order: azure-cvm - tpm - sev-snp - tdx . The first provider whose detect succeeds is selected. opaque is a not-yet-implemented placeholder: it is excluded from auto-detect, and selecting it explicitly raises ATTESTATION PROVIDER NOT IMPLEMENTED rather than falling through silently. If no hardware provider is detected, the gateway starts only under CMCP DEV MODE=1 a non-attested software-only fallback and otherwise refuses to start. python from cmcp runtime.config import TEEProvider Auto-detect default attestation.provider: auto - azure-cvm - tpm - sev-snp - tdx software-only is used only under CMCP DEV MODE=1 Explicit hardware selection attestation.provider: sev-snp OPAQUE Managed Runtime opt-in only; not yet implemented OPAQUE ATTESTATION URL=https://... cmcp start --config cmcp-config.yaml | Mode | Behavior | Use case | |---|---|---| enforcing | Policy denies return HTTP 403; call is not forwarded | Production | advisory | Policy denies are logged; call proceeds | First deployment, policy tuning | silent | Policy is evaluated but nothing is logged or blocked | Baselining | Default is enforcing . Set enforcement mode: advisory in cmcp-config.yaml to use advisory mode. cmcp-config.yaml full reference: attestation: provider: auto auto | tpm | sev-snp | tdx | opaque | software-only enforcement mode: enforcing enforcing | advisory | silent validity seconds: 86400 attestation freshness window default: 24 hours staleness policy: fail closed fail closed | warn only expected measurement: ~ pin a specific PCR/measurement optional policy bundle path: policies/ directory containing .cedar files and manifest.json catalog path: catalog.json approved tool catalog listen addr: "0.0.0.0:8443" max response size bytes: 2097152 2 MB default policy reload interval seconds: 0 0 = disabled; restart required to update policy Environment variables: | Variable | Effect | |---|---| CMCP DEV MODE=1 | Use software-only TEE provider; no hardware required | CMCP BEARER TOKEN | Require this bearer token on all inbound requests | OPAQUE ATTESTATION URL | Enable OPAQUE Managed Runtime attestation explicit opt-in | | Command | Flags | Description | |---|---|---| cmcp start | --config PATH required | Start the gateway | cmcp validate-config | --config PATH required | Validate cmcp-config.yaml without starting | cmcp validate-bundle | --bundle-path PATH required , --expected-hash sha256: