MCP.Market

Knowmint MCP server

by Sou0327·io.github.Sou0327/knowmint·v0.1.4·3 stars

AI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana.

B72/100grade B
What users say
No reviews yet
Be the first
Safety scan
B72/100

full report

Adoption
New

3 stars32 downloads/wk

Reviews

Write one

Nobody has reviewed Knowmint yet.

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

Knowmint tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan4 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 164 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 72/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Knowmint compares

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

Safety score
72/100
higher than 40% of 4,460 AI and agents servers
GitHub stars
3
more than 75% of 2,711 AI and agents servers
Downloads a week
32
more than 20% of 1,538 AI and agents servers with a package

Install Knowmint in Claude Code, Cursor or VS Code

Runs npx -y @knowmint/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add knowmint -- npx -y @knowmint/mcp-server
Add to Cursor

What the publisher says

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

KnowMint

The first knowledge marketplace where AI agents pay directly with SOL — autonomously.

Humans list tacit knowledge, experiential insights, and battle-tested solutions. AI agents (Claude Code, ElizaOS, AgentKit) autonomously discover, evaluate, and purchase via the x402 protocol — paying sellers directly via non-custodial Solana P2P transfers. No private keys held by the platform.

Human-in-the-loop mode also available: agent searches and proposes, you approve. Same marketplace, your choice of autonomy level.

Three access layers: Web UI / CLI (km) / REST API + MCP Server

Web UI

CLI / MCP (for AI Agents)

Why KnowMint

  • First for agentic payments — AI agents autonomously pay with SOL via x402 protocol. No human required to complete a purchase
  • x402 autonomous purchasing — HTTP 402 + Solana P2P direct transfer. Agent finds, pays, and accesses knowledge end-to-end
  • Human-in-the-loop also available — Agent proposes, you approve. Same marketplace, your choice of autonomy level
  • Human → AI knowledge supply — Sell experiential and tacit knowledge that AI cannot self-generate
  • Non-custodial payments — Buyer-to-seller P2P direct transfer on Solana (no platform custody)

For AI Agents

Getting an API Key

For AI agents (wallet-based, no web UI needed):

  1. POST /api/v1/auth/challenge with { "wallet": "", "purpose": "register" }
  2. Sign the returned message with your Solana wallet
  3. POST /api/v1/auth/register with { "wallet", "signature", "nonce" }
  4. Receive { "apikey": "km...", "user_id", "wallet" } — ready to use

For humans (web UI):

  1. Sign up at knowmint.shop (or your self-hosted instance)
  2. Go to Profile → API Keys
  3. Create a key with read or write permission
  4. Copy the key — it is shown only once

MCP Server

Add to ~/.claude/mcp.json:

{
  "mcpServers": {
    "knowmint": {
      "command": "npx",
      "args": ["--yes", "--package", "@knowmint/mcp-server@0.1.2", "mcp-server"],
      "env": {
        "KM_BASE_URL": "https://knowmint.shop"
      }
    }
  }
}

No API key needed for initial setup. The agent can self-register using km_register.

Self-Registration (No Prior Account Needed)

  1. Prepare a Solana keypair file (e.g. ~/.config/solana/id.json)
  2. Call km_register with the keypair path — the tool handles challenge, signature, and registration automatically
  3. The API key is saved to ~/.km/config.json and used for all subsequent calls
km_register(keypair_path: "~/.config/solana/id.json")
  → POST /api/v1/auth/challenge (get nonce)
  → Sign message with keypair
  → POST /api/v1/auth/register (get API key)
  → Saved to ~/.km/config.json — ready to use

To re-login to an existing account: kmwalletlogin(keypair_path: "...").

Tool Reference

x402 Autonomous Purchase Flow

km_get_content()
  → HTTP 402 (payment_required)
  → Solana transfer
  → Retry with payment_proof
  → Content returned

Shortened. The full README is on GitHub.

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

Knowmint: common questions

Is Knowmint MCP server safe?
Mostly: it is graded B (72/100). Read the Knowmint safety report
How do I install Knowmint?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Knowmint need an API key?
Yes. The registry entry asks for KM_API_KEY.
Is Knowmint maintained?
The last commit was 202 days ago (2026-04-16). The latest release is v0.1.4.
What can I use instead of Knowmint?
Servers from other publishers that do the same job: three.ws Marketplace MCP server, Basic Memory MCP server and IWE (iwe.md) MCP server.
How does Knowmint compare with other AI and agents MCP servers?
safety score 72/100 (higher than 40% of 4,460 AI and agents servers); github stars 3 (more than 75% of 2,711 AI and agents servers); downloads a week 32 (more than 20% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to Knowmint

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

  • three.ws Marketplace
    Browse and discover the public three.ws agent marketplace and skills catalog. Read-only.
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A
  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A