Skip to content
NessGate logo

NessGate

Reads a domain's published machine-readable files like llms.txt, ARD and API catalogs and returns one normalized, source-linked answer.

At a glanceswept 2026-10-13

1k installs/mo

Emerging

For
Developers building AI agents that need to discover what a domain publishes, and domain owners checking their machine-readable files
Price
Price not read
Activity
Actively maintainedrelease 10 days ago
Company
Domain since 2026domain registered
Runs as
API
What people do with it
  • resolve a domain's machine-readable resources in one request
  • generate a connection plan matched to a client's capabilities
The companyeach fact with its source · read 2026-10-14
  • Domain since2026domain registered
How a program reaches itfound, not claimed · read 2026-10-14
  • MCP servercom.nessgate/nessgateverified in the MCP registry
  • Stateanswers, 3 toolschecked 2026-10-14
  • Address to connectnessgate.com/mcp
  • OpenAPI spec4 pathsthe spec ↗
  • API docsnessgate.com/apithe vendor's page ↗

MCP server details →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Developer toolsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

All Developer tools tools →

Questions this page answers
  • What is NessGate?

    Reads a domain's published machine-readable files like llms.txt, ARD and API catalogs and returns one normalized, source-linked answer. It is listed in the Atlas under Developer tools.

  • Who is NessGate for?

    Developers building AI agents that need to discover what a domain publishes, and domain owners checking their machine-readable files

  • Do people use NessGate?

    Emerging: 1k installs/mo (npm).

  • Is NessGate still maintained?

    Actively maintained: release 10 days ago.

  • What are alternatives to NessGate?

    In Developer tools, by use: Merge, Kilo, CometChat, FastMCP, AIsa, cognee.

Not quite it? Describe the job

beta

Five tools from the Atlas that fit it, each judged against what you wrote.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.