MCP.Market

Agent Gate MCP server

by forgeorbital.com·com.forgeorbital/agent-gate·v0.1.5
No reviews yet

Local mandate gate and proof trail for AI agents that take consequential actions.

C58/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C58/100

full report

Adoption
New

76 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Gate yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Gate tools (7, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • cancel_orderwrite action

    Cancel a resting order. Blocked when the kill switch is engaged or the venue is not whitelisted. Recorded to Forge.

  • gate_action

    Check one consequential agent action against the signed mandate and record the Forge proof trail. It returns allow, escalate, or block. It does not execute the action.

  • gate_status

    Report the active mandate summary, allowed action types, kill-switch state, and whether trading venue tools are available.

  • get_market

    Fetch one market by id/ticker (read-only passthrough).

  • get_markets

    List markets on a venue (read-only passthrough). Does not place any trade.

  • get_positions

    List current open positions on a venue (read-only passthrough).

  • place_orderwrite action

    Submit an order for evaluation by the local risk mandate. Executes ONLY if the mandate allows it; a block or escalate is returned without touching the venue. Every outcome is recorded to Forge as a verifiable proof trail.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan53 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancerepository not readable: repo not found3/15
  • Maintainer identityverified namespace with website, no repo4/10
Overall 58/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Gate compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
58/100
higher than 15% of 4,460 AI and agents servers
Tools
7
the typical AI and agents server has 6
Tools that change things
29%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
76
more than 57% of 1,538 AI and agents servers with a package

What its tools let an agent do: 5 read · 1 change · 1 delete

Install Agent Gate in Claude Code, Cursor or VS Code

Runs npx -y forge-agent-gate on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-gate -- npx -y forge-agent-gate
Add to Cursor

Agent Gate: common questions

Is Agent Gate MCP server safe?
With care: it is graded C, so read the findings first (58/100). Read the Agent Gate safety report
How do I install Agent Gate?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Gate need an API key?
Yes. The registry entry asks for FORGE_API_KEY, FORGE_BEARER_TOKEN, KALSHI_API_KEY_ID.
Is Agent Gate maintained?
The latest release is v0.1.5.
What can I use instead of Agent Gate?
Servers from other publishers that do the same job: Decionis MCP server, Emilia Protocol MCP server and Agent-Native Chat MCP server.
How does Agent Gate compare with other AI and agents MCP servers?
safety score 58/100 (higher than 15% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Gate

Same job from other publishers: the closest match first, then the best rated.

  • Decionis
    Authorize consequential AI agent actions before execution
    More from decionis.com →
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • three.ws Provenance
    Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
    More from nirholas →
    B
  • Claude Prompts
    Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
    A