Observed by Atlas — nobody has proved they control this domain. Is it yours?
Manufact
OBSERVEDDeploy, test, and monitor MCP servers for ChatGPT and Claude
- FRESHNESS
- 0.83
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 4
- BOT-FILTERED
- FIRST SEEN
- SEP 3
- IN THE FLOW

Manufact is a platform for building, deploying, testing, publishing, and monitoring MCP (Model Context Protocol) servers that connect to AI chat and coding agents such as ChatGPT and Claude. It offers hosting from a Git repository, template, or CLI, cross-client test harnesses, publishing checklists for app marketplaces, and analytics on tool calls and sessions. It is built around the open-source mcp-use SDK and is aimed at developers and teams shipping MCP servers and apps.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
$5 in credits included monthly · 2 projects · 30k requests/mo · 1 team member · Publishing checklist
$300 billed yearly · 5 projects · 300k requests/mo · 3 team members · Test suites (evals)
$3,000 billed yearly · Unlimited projects · 3M requests/mo · 10 team members · Preview deployments
Starts at $1,000/month · Unlimited projects · Unlimited requests/mo · Unlimited team members · Priority support
Every crawl is diffed. Material changes are listed.
Nobody has vouched for Manufact yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about Manufact? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it