MCP.Market

Gather MCP server

online · 100% uptime
by hunta-ai·io.github.hunta-ai/gather·v0.1.0
No reviews yet

Attestable memory for AI agents: curated writes, verifiable tenant isolation, bi-temporal facts.

A88/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Gather yet.

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

Gather tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

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

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 2647ms (auth required)17/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Gather compares

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

Safety score
88/100
higher than 75% of 48,255 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
614 ms
faster than 23% of 30,031 servers

Install Gather in Claude Code, Cursor or VS Code

claude mcp add --transport http gather https://mcp.hunta.ai/mcp
Add to Cursor

What the publisher says

From the Gather repository's README, as published. We do not edit it. Read it on GitHub

Gather

Deterministic, attestable memory for AI coding agents.

Get started · Console · How it works · Compare

This repo is the open integration surface for Gather, a multi-tenant org-memory service (an MCP server plus a REST API) with server-enforced tenant isolation and attestable, curated writes. The memory engine is a hosted service; this repo holds the client integrations (starting with the Claude Code plugin) so your harnesses use that memory automatically, instead of hoping the model remembers to.

What's here

More integrations (Codex, Agent SDK) land here over time.

Quickstart (Claude Code)

Two lines, then a token:

/plugin marketplace add hunta-ai/gather
/plugin install gather@hunta

Mint an agent key in the console (scoped to propose + recall, never to write canon), then point the plugin at your tenant:

export GATHER_URL=https://mcp.hunta.ai   # or your own deployment on Estate (self-host)
export GATHER_TOKEN=<your-agent-key>

Recall and capture are live on your next session. Full walkthrough: hunta.ai/get-started.

Using another client (raw MCP)

Not on Claude Code, or prefer raw MCP? Point any MCP client at the server directly (see examples/mcp-config.json):

{
  "mcpServers": {
    "gather": {
      "url": "https://mcp.hunta.ai/mcp",
      "headers": { "Authorization": "Bearer <your-agent-key>" }
    }
  }
}

What the plugin does

facts into the turn, so the agent starts with what it already knows.

  • Auto-recall on every prompt. A UserPromptSubmit hook queries your memory and injects the top

survives Claude Code's context resets.

  • Re-inject after compaction. A SessionStart(compact) hook re-runs recall so injected context

your staging inbox. The transcript is never uploaded.

  • Loss-proof capture. PreCompact and SessionEnd hooks post a content-free breadcrumb to

shows local recall hit-rate and latency.

  • Curation skills. /gather:flush reviews pending candidates; /gather:status

The principle is harness-enforced invocation: tool availability is not tool use. Agents do not reliably recall context or write learnings back on their own, so the hooks make it happen by construction, on every turn, without depending on the model's judgement.

How memory works

Gather's differentiator is the write path: the writer never decides.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Gather: common questions

Is Gather MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Gather safety report
How do I install Gather?
It runs remotely at mcp.hunta.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Gather need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Gather maintained?
The last commit was 40 days ago (2026-09-25). The latest release is v0.1.0.
Is Gather up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Gather?
Servers from other publishers that do the same job: Knowl MCP server.
How does Gather compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 614 ms (faster than 23% of 30,031 servers). Full comparison.

Alternatives to Gather

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

  • Knowl
    Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.
    A