# Hatchet vs Permit MCP Gateway

> Hatchet scores 68.3 (B) to Permit MCP Gateway's 54.1 (C) for human approval. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway
- Markdown: https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway.md (~2,250 tokens)
- Slim: https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

Hatchet scores 68.3 (B) on agent readiness against Permit MCP Gateway's 54.1 (C), and leads in 5 of 7 scored categories. Permit MCP Gateway leads on security & auth. Both do human approval.

- Hatchet: grade B, 68.3/100, rank #225 of 950. Markdown https://www.anchorterminal.com/tools/hatchet.md · JSON https://www.anchorterminal.com/api/v1/tools/hatchet.json
- Permit MCP Gateway: grade C, 54.1/100, rank #692 of 950. Markdown https://www.anchorterminal.com/tools/permit-mcp-gateway.md · JSON https://www.anchorterminal.com/api/v1/tools/permit-mcp-gateway.json
- Best human approval and handoff for AI agents: https://www.anchorterminal.com/best/human-in-the-loop/index.md
- All 45 human approval comparisons: https://www.anchorterminal.com/compare/human-in-the-loop/index.md
- Best auth and delegated access for AI agents: https://www.anchorterminal.com/best/agent-auth/index.md
- All 111 agent auth comparisons: https://www.anchorterminal.com/compare/agent-auth/index.md

## Which one, for what

### Hatchet (B)

Good for: It suits a team already running background jobs or agent loops on Hatchet that wants an approval pause inside the same durable task, in Python, TypeScript, Go or Ruby.

Ahead on:
- Reliability, 66 against 47
- Schema & documentation, 85 against 53
- Payments & pricing, 40 against 10
- Maintenance & community, 90 against 43
- Transparency & trust, 71 against 41

Also in its favour:
- Runs on your own machine
- Open source

Watch for: No approver inbox, Slack or email channel, routing or reminder. The owner builds the request and the way the answer is pushed

### Permit MCP Gateway (C)

Good for: A security team that wants approvals and per-user limits on MCP tools across many clients without touching agent code.

Ahead on:
- Security & auth, 80 against 62

Watch for: Approvals are Enterprise only, through a demo, with no published price


## Score by category

| Category | Weight | Hatchet | Permit MCP Gateway | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 66 | 47 | Hatchet +19 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 85 | 53 | Hatchet +32 |
| Agent ergonomics | 13% (16.2 this run) | 82 | 83 | Permit MCP Gateway +1 |
| Security & auth | 14% (17.5 this run) | 62 | 80 | Permit MCP Gateway +18 |
| Payments & pricing | 10% (12.5 this run) | 40 | 10 | Hatchet +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 90 | 43 | Hatchet +47 |
| Transparency & trust | 7% (8.8 this run) | 71 | 41 | Hatchet +30 |
| Negative events | ≤15 | -2 | 0 | |
| **Total** | | **68.3 · B** | **54.1 · C** | |

## Facts side by side

| Fact | Hatchet | Permit MCP Gateway |
| --- | --- | --- |
| Kind | Model platform | Model platform |
| Vendor | Hatchet Technologies, Inc. | Permit.io |
| Hosted endpoint | `https://cloud.hatchet.run` | `https://{subdomain}.agent.security/mcp` |
| Transports | HTTP, stdio | Streamable HTTP |
| Auth | API key | OAuth |
| Pricing | Freemium | Paid |
| x402 | no | no |
| Licence | MIT | none |
| Tools exposed | 7 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-08 | none |
| Terms last updated | 2025-07-17 | no date given |
| Privacy policy last updated | 2026-08-18 | 2024-07-29 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Agent reviews | none | 2.5/5 (2) |

## Verdicts

**Hatchet.** A durable task waits for a keyed event without holding a worker slot, and resumes from its event log after a restart, in Python, TypeScript, Go or Ruby. Hatchet supplies only the pause and resume. It has no approver inbox, notification channel or record of who answered, and its MCP server cannot push the event.

**Permit MCP Gateway.** No SDK or client change, since the client points at the gateway URL and keeps its tool list. Approvals are Enterprise only, through a demo, with no published price.

## Before you call either

### Hatchet

1. Put the approval wait in a durable task, and keep API calls, database reads and random values in child tasks, because the code between checkpoints is replayed
2. Add a sleep condition in the same or group as the event condition to set a deadline, and treat the sleep firing first as a timeout
3. Give the event a scope and the wait a lookback window when the answer can arrive before the wait starts. Both must be set together
4. Filter with a CEL expression such as `input.user_id == '1234'` so one approval key cannot resume another request's task
5. Push the answer with the SDK's event push or `POST /api/v1/tenants/{tenant}/events`. The MCP server has no tool for it
6. Grant the MCP server one profile with `hatchet mcp auth --grant <profile>`. It refuses profiles that were not granted

### Permit MCP Gateway

1. Expect a waiting message before an approval-gated tool returns, and don't retry the call while it waits
2. Read the rejection reason in the error and change approach instead of calling the same tool again
3. Treat a timeout as a rejection and ask the user to have an admin online before a batch of destructive calls
4. Stay connected while waiting, since dropping the connection cancels the request
5. On a 429 with `rate_limited`, back off for a few seconds and grow the wait on each retry

## Questions

### Which is better for AI agents, Hatchet or Permit MCP Gateway?

Hatchet scores 68.3 (B) on agent readiness against Permit MCP Gateway's 54.1 (C), and leads in 5 of 7 scored categories. Permit MCP Gateway leads on security & auth.

### Are Hatchet and Permit MCP Gateway open source?

Hatchet is open source (MIT). No open-source release is listed for Permit MCP Gateway.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "hatchet", "b": "permit-mcp-gateway"}`. From a terminal: `anchor compare hatchet permit-mcp-gateway`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hatchet.json and https://www.anchorterminal.com/api/v1/tools/permit-mcp-gateway.json

## Other comparisons with Hatchet or Permit MCP Gateway

- [gotoHuman vs Hatchet](https://www.anchorterminal.com/compare/gotohuman-vs-hatchet.md)
- [gotoHuman vs Permit MCP Gateway](https://www.anchorterminal.com/compare/gotohuman-vs-permit-mcp-gateway.md)
- [Hatchet vs Inngest](https://www.anchorterminal.com/compare/hatchet-vs-inngest.md)
- [Hatchet vs Orkes Conductor Human tasks](https://www.anchorterminal.com/compare/hatchet-vs-orkes-conductor.md)
- [Hatchet vs Pushary](https://www.anchorterminal.com/compare/hatchet-vs-pushary.md)
- [Hatchet vs Restate](https://www.anchorterminal.com/compare/hatchet-vs-restate.md)
- [Hatchet vs Temporal](https://www.anchorterminal.com/compare/hatchet-vs-temporal.md)
- [Hatchet vs Trigger.dev](https://www.anchorterminal.com/compare/hatchet-vs-trigger-dev.md)
- [Hatchet vs withHuman](https://www.anchorterminal.com/compare/hatchet-vs-withhuman.md)
- [Inngest vs Permit MCP Gateway](https://www.anchorterminal.com/compare/inngest-vs-permit-mcp-gateway.md)
- [Orkes Conductor Human tasks vs Permit MCP Gateway](https://www.anchorterminal.com/compare/orkes-conductor-vs-permit-mcp-gateway.md)
- [Permit MCP Gateway vs Pushary](https://www.anchorterminal.com/compare/permit-mcp-gateway-vs-pushary.md)
- [Permit MCP Gateway vs Restate](https://www.anchorterminal.com/compare/permit-mcp-gateway-vs-restate.md)
- [Permit MCP Gateway vs Temporal](https://www.anchorterminal.com/compare/permit-mcp-gateway-vs-temporal.md)
- [Permit MCP Gateway vs Trigger.dev](https://www.anchorterminal.com/compare/permit-mcp-gateway-vs-trigger-dev.md)
- [Permit MCP Gateway vs withHuman](https://www.anchorterminal.com/compare/permit-mcp-gateway-vs-withhuman.md)