
Irontrellis Gateway
io.github.zerohourzuluPublished by GitHub account zerohourzuluv1.0.0-rc.2Updated Oct 30, 2026
Local MCP gateway: approved tools behind a signed authority check, per call or as exactly-once jobs
Overview
Local stdio MCP gateway that puts approved upstream tools behind a signed authority history, with per-call checks or exactly-once jobs.
- What you can do
- Route approved upstream MCP tools through a gateway that re-reads the signed authority history on every call
- Run exactly-once jobs that reconcile a repeat to the original retained attempt instead of forwarding again
- Run per-call tools where each call is checked against current authority and the configured tool definition
- Refuse calls whose upstream tool definition changed, whose grant was revoked, or whose arguments conflict
- Return recorded outcomes such as RESPONSE_RETAINED, RECONCILIATION_ONLY, DENIED or OUTCOME_UNKNOWN
- Inspect, revoke and recover through a separate operations CLI and programmatic subpaths
- When to use it
- Use it when an assistant calls upstream MCP tools that must respect revocable grants and must not repeat a side-effecting request after a lost reply. It suits operators who can keep the history, signers, clock and upstream configuration outside the model's control.
- Requirements
- A local Node.js runtime and a global install of the npm package, which provides the gateway and operations commands. A gateway configuration file created by the setup command, with a private directory for its history and on-disk attempt state. The server speaks stdio and waits for an MCP client; no environment variables or headers are declared.
Installation
In SourceWeft
- Open Irontrellis Gateway in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
IronTrellis MCP Gateway
@ramex-labs/irontrellis-mcp-gateway 1.0.0-rc.2.3 puts the MCP tools you approve behind IronTrellis (formerly Continuity), which keeps a signed, replayable history of what each AI agent may do. Before a call reaches an upstream tool, the gateway checks the agent's current authority in that history (format 2); for exactly-once jobs and recorded calls, it also keeps the state of the attempt on disk. MCP client and server dependencies are pinned to 2.2.0.
What it is for
An agent that calls its tools directly can act on authority that was taken away a minute ago, or send the same request twice after a lost reply. The gateway sits between your MCP client and the upstream MCP servers you approve, and handles these cases:
Try it on a synthetic case
Install from the next tag, or use a verified packed installation; the 1.0.0-rc.2 build is not claimed publicly released.
setup creates a format-2 history with one worker agent, two local upstream servers (documents and tickets) and two jobs, read_incident and create_incident_ticket (two tools of the same names in per-call mode). The worker's grants and session expire after an hour. From your MCP client:
The server speaks stdio and waits for an MCP client. The setup is a disposable case with local credentials and synthetic tools. Protect its private directory and never reuse its credentials in production. An unknown outcome needs investigation of the original business key, not a new key to force a retry.
Choose an execution mode
The profile name is not a guarantee of exactly-once effects inside an arbitrary upstream service. A query-only ALLOW is not a dispatch permit.
enforceFromReadOnlyHistory (set by hand) keeps enforcing from a never-migrated legacy or format-1 history read-only: every open warns, and it serves only calls that need no record: a call that must be recorded is refused (FORMAT_READ_ONLY with a remedy) before anything is dispatched. Migrate to write.
Keep the authenticated history ID/domain, agent, runtime session, signers, role/tenure, trusted clock, upstream executable, business mapping and storage outside agent control. A model supplies only the bounded business arguments permitted by the fixed schema. Retiring or revoking authority cannot undo an effect already sent.
Public imports
The four subpaths in bold are separate capabilities; importing one does not enable another or establish a secure public deployment. Public HTTPS deployment is not part of this release. Each subpath has its compiled runtime and declaration exports and a default export key.
The loopback HTTP helper is an evaluation profile. The router/backend profile requires its explicit TLS/mTLS configuration, pinned private peer, channel-bound assertions, nonce storage and independent bearer/Core checks. Trusted isActive and current-access guards must remain effective across asynchronous work. A token or authenticated transport is not native authority to perform an operation. HTTP and Tasks do not turn an uncertain effect into a new attempt.
Records and results
A refusal decided by the history is returned with its recording status; a recording failure cannot turn a refusal into ALLOW. Core and budget refusals are distinguished from connector reports. Upstream effect or receipt fields are assertions under the connector/counterparty profile; replay does not prove an external business outcome. Replies retain externalOutcome: NOT_PROVEN where applicable.
Every message from the agent is checked before the MCP layer sees it: at most 16 KiB, strict JSON, and no more than 1,024 messages within any 60 seconds. A flood ends the gateway (INPUT_REFUSED); a long session of ordinary calls does not. Upstream servers are bounded the same way, and one that stops or floods is disconnected and started again, with its tool definition checked, on the next governed call to it.
Access is checked again after the attempt is durably retained and immediately before the call enters the upstream tool. A revocation at that point prevents the new effect, while an attempt already admitted keeps its uncertain state. No callback, old approval or retained result can replace that check.
Use operations, recovery and access-policy for operator procedures. Snapshot contents are sensitive; protect them as credentials/evidence until the chosen profile's exclusions are verified. Never clear a live lock or recovery journal to make a stuck operation run again.
Optional anchoring barrier
Privileged hosts can configure the live anchoring barrier through the programmatic API. It retains an admitted request while waiting for eligible protected reports, checks a stop latch, and resumes only while no dispatch start exists. The CLI setup does not enable anchoring.
Know its limits in 1.0.0-rc.2. This build includes no qualified report producer, and nothing in it verifies a chain anchor: verifyAnchor returns no report, irontrellis verify takes none, and the diagnostic connector reports cannot release this barrier. A production-profile barrier therefore never opens unless an external producer supplies reports, and it takes the mode a report declares, CONSENSUS_VERIFIED included, on that producer's word. No consensus-verified anchoring is claimed; the separate tools used for the demonstration anchoring records report TRUSTED_NODE only, never consensus-verified.
Established and not established
The package's tests cover the real engine, crash and retry, transport, strict declarations and a packed install. The source tests are src/http-test.test.mjs, src/cooperative-test.test.mjs and src/http-twohop-test.test.mjs; the packed verifier is src/http-verify-install.py with the selected offline dependencies. These are the package's own tests; no separate review of the transport subpaths is claimed here.
This is not a hostile-code sandbox, distributed transaction manager, proof of downstream success or production chain/finality implementation. Upstreams share the configured host trust boundary. Cooperating destinations need their own checkpoint, fencing and deduplication contract. Whole-directory rollback, compromised administrators, a destination's unseen revocation and irreversible effects after dispatch remain distinct risks.
What the gateway records (admissions, refusals, effects, receipts) is signed with runtime session keys, not the owner key, so it stays unattested and unwitnessed until the next owner write; see operations. The attestation policy for PHL, Proof of Human Lineage (ATTESTED), ships in the 1.0.0-rc.2 core; transport test success does not establish every such policy combination.
Dependencies: @ramex-labs/irontrellis, @ramex-labs/irontrellis-remote, jose, @modelcontextprotocol/server and @modelcontextprotocol/client (jose 6.2.12 and the MCP SDK 2.2.0, pinned exactly). Apache-2.0.
Last reviewed: 24 October 2026. This page is revisited at each release.
Source: packages/mcp-gateway/README.md at commit cd34ad7
Tools
0Version history
1- v1.0.0-rc.2LatestOct 29, 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 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 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