FaceabotCapability network for AI agents
‹ Back

Catalog › io.github.acarchidi/agentforge

Is agentforge reliable?

Reliable (measured) Yes. Faceabot measured agentforge 66 times: 100% of checks succeeded, including the last 66 in a row (last check 2026-11-21 12:35 UTC). It also does the job: its real read-only task worked 6 of 6 times.

Last check: 2026-11-21 12:35 UTC · answered in 1085 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Safety checks for AI agents: preflight before signing, prompt-injection scan, sanctions, rug checks.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.13.1 · publisher website
Connect your agent
{
  "mcpServers": {
    "agentforge": {
      "url": "https://agentforge-taupe.vercel.app/mcp"
    }
  }
}
Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.acarchidi/agentforge"} on https://faceabot.com/api/mcp.
Does it actually do the job?

Does the job (tested) — Faceabot asked gas_oracle to do a small read-only task 6 time(s): 6 returned a real result, the last 6 in a row. Last result: ok in 869 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.
Other proven tools for the same job

Agent safety checks: prompt-injection scan, honeypot check, x402 preflight + crypto data (USDC/x402) Reliable (measured) · 100%
Checks before an agent acts: prompt-injection scan, honeypot check, x402 preflight. 3 free calls. · https://angel.oroboros-design.com/agenten/signal/mcp

Pre-transaction Safety Checks (Tanod) Reliable (measured) · 100%
Safety checks before you sign, pay or install: contract, token and package scans, phishing, OFAC. · https://tanod.dev/mcp/security

Invoice Preflight Reliable (measured) · 98%
Evidence-backed UBL, PDF, and image invoice checks before approval or payment. · https://mcp.dropenginehq.com/api/invoice-mcp

Picked from Faceabot's live measurements. Or let Faceabot choose: GET https://faceabot.com/resolve?need=…
Faceabot measurements
WhenAnswersReal taskLatency
2026-11-21 12:35 UTC✅ ok✅ done1085 ms
2026-11-17 23:40 UTC✅ ok✅ done1654 ms
2026-11-14 11:30 UTC✅ ok✅ done2604 ms
2026-11-11 00:35 UTC✅ ok✅ done1071 ms
2026-11-07 11:25 UTC✅ ok✅ done1120 ms
2026-11-04 00:35 UTC✅ ok✅ done759 ms
2026-10-31 09:55 UTC✅ ok—1559 ms
2026-10-27 12:50 UTC✅ ok—7550 ms
2026-10-27 12:50 UTC✅ ok—3830 ms
2026-10-27 02:05 UTC✅ ok—2940 ms
2026-10-26 15:10 UTC✅ ok—4781 ms
2026-10-26 02:10 UTC✅ ok—5679 ms
2026-10-25 11:31 UTC✅ ok—3536 ms
2026-10-25 00:40 UTC✅ ok—7915 ms
2026-10-24 14:30 UTC✅ ok—5797 ms
2026-10-24 04:50 UTC✅ ok—8477 ms
2026-10-23 18:11 UTC✅ ok—6720 ms
2026-10-23 07:47 UTC✅ ok—6390 ms
2026-10-22 21:20 UTC✅ ok—4208 ms
2026-10-22 10:05 UTC✅ ok—5927 ms
Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Find tools similar to agentforge →

Publisher of agentforge?

Show your measured reliability on your README or website:

Faceabot reliability badge for agentforge

[![Measured by Faceabot](https://faceabot.com/badge/io.github.acarchidi/agentforge.svg)](https://faceabot.com/tools/io.github.acarchidi/agentforge)
Data in JSON: /api/catalog?id=io.github.acarchidi/agentforge · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms