Scopeblind Gateway MCP Server

Fail-closed Cedar policy gate + Ed25519 signed receipts for AI agent tool calls. Denies on any policy error, proves the gate is live with a startup

Remote serverstreamable-http

What is the Scopeblind Gateway MCP server?

Most developer tooling work still happens through a UI a human drives. Scopeblind Gateway MCP server moves it into the conversation instead. Fail-closed Cedar policy gate + Ed25519 signed receipts for AI agent tool calls. Denies on any policy error, proves the gate is live with a startup self-test, and turns every decision into a local searchable record you own. The open gate.

The short version

  • Fail-closed by default. — On any policy error, a missing engine, or an
  • It proves its own restraint. — serve --enforce and doctor run a startup
  • Every decision is a receipt anyone can verify. — Decisions are Ed25519-signed

The tools it exposes

The server publishes 14 tools. What each one is for:

  • serve — Start the HTTP hook server for Claude Code (port 9377). --enforce runs the restraint self-test first; --cedar and --policy select the
  • init — Generate an Ed25519 keypair (keys/gateway.json), a config template, and a sample policy
  • sample — Seed a clearly-labeled sample record (8 decisions: one blocked call, two payments; kid sample-demo) plus a tampered copy, so record, claim
  • policy — See and change the Cedar policy from the terminal: policy list (permit / forbid / default-deny per tool, with how often the gate allowed or denied
  • wrap — Print a protected MCP command or patch Claude Desktop MCP servers. Dry-run by default; use --write to update Claude Desktop config
  • dashboard — Start a local-only dashboard on 127.0.0.1 showing tool inventory, risk, policy coverage, exact-action approvals, receipt chains, and audit export
  • recommend — Draft a reviewable JSON policy from observed local calls. Dry-run by default; use --write to create protect-mcp.recommended.json
  • registry — Create an org identity, anchor receipt digests, and write a static verifier page. Hosted mode uploads digests only
  • record — Open a local, searchable viewer over your receipts (--live streams as the agent runs): Ed25519 signatures verified in your browser against your
  • claim — Mint a signed, position-blind attestation of a predicate over the record (--no incl. --no payment, --only <c1,c2>, --no-verdict
  • anchor-record — Checkpoint the record's Merkle root + count + time range into the public log (heartbeat-friendly: skips when unchanged). A later claim whose
  • verify-claim — Verify a claim pack offline: signature, recomputed Merkle root, independently recomputed predicate, and the anchor sidecar when present (binds the

What it needs from you

Configuration is passed through the environment: SCOPEBLIND_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Scopeblind Gateway's toolset — serve, init, sample and 11 more — is a fair guide to whether it matches your workflow. It is maintained by scopeblind; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Scopeblind Gateway.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
serveStart the HTTP hook server for Claude Code (port 9377). --enforce runs the restraint self-test first; --cedar <dir> and --policy <path> select the policy.
initGenerate an Ed25519 keypair (keys/gateway.json), a config template, and a sample policy.
sampleSeed a clearly-labeled sample record (8 decisions: one blocked call, two payments; kid sample-demo) plus a tampered copy, so record, claim, verify-claim, and anchor-record are replayable from scratch before wiring an age
policySee and change the Cedar policy from the terminal: policy list (permit / forbid / default-deny per tool, with how often the gate allowed or denied it), policy show, policy allow <tool>, policy deny <tool>, policy path. A
wrapPrint a protected MCP command or patch Claude Desktop MCP servers. Dry-run by default; use --write to update Claude Desktop config.
dashboardStart a local-only dashboard on 127.0.0.1 showing tool inventory, risk, policy coverage, exact-action approvals, receipt chains, and audit export.
recommendDraft a reviewable JSON policy from observed local calls. Dry-run by default; use --write to create protect-mcp.recommended.json.
registryCreate an org identity, anchor receipt digests, and write a static verifier page. Hosted mode uploads digests only.
recordOpen a local, searchable viewer over your receipts (--live streams as the agent runs): Ed25519 signatures verified in your browser against your gateway key, capability tags, a provenance tree, and one-click signed export
claimMint a signed, position-blind attestation of a predicate over the record (--no <cap> incl. --no payment, --only <c1,c2>, --no-verdict <verdict>, --count <verdict>, --payment-under <cap>), disclosing only decision categor
anchor-recordCheckpoint the record's Merkle root + count + time range into the public log (heartbeat-friendly: skips when unchanged). A later claim whose commitment matches an anchored checkpoint is provably over the complete record
verify-claimVerify a claim pack offline: signature, recomputed Merkle root, independently recomputed predicate, and the anchor sidecar when present (binds the anchored envelope to this exact claim, then confirms the public log holds
killer-demoGenerate a complete shadow-mode to policy to approval to signed-receipt demo pack.
verify-disclosureVerify a scopeblind.selective_disclosure.v0 package and explain disclosed versus hidden fields.

How to install the Scopeblind Gateway MCP server

{
  "mcpServers": {
    "scopeblind-gateway": {
      "command": "npx",
      "args": ["-y", "protect-mcp"],
      "env": {
        "SCOPEBLIND_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
SCOPEBLIND_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Scopeblind Gateway to serve.
  • Use Scopeblind Gateway to init.
  • Use Scopeblind Gateway to sample.

Frequently asked questions

It connects Scopeblind Gateway to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (serve, init, sample, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Scopeblind Gateway directly.