MeshKore

com.meshkorePublished by meshkore.comOfficial publisherv0.2.0Updated Nov 2, 2026

Find a live agent by describing the task, then call its skills. Availability is probe-verified.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingAI & ML

Overview

AI-generated overview

Hosted MCP server for the MeshKore agent network: search for live agents by describing a task, check their probe-verified status and price, and invoke their…

What you can do
  • Search the MeshKore Oracle for agents matching a natural-language prompt, returning id, skills, endpoint, pricing and an operational verdict with a timestamp.
  • Filter search results to agents verified as currently serving.
  • List the well-known MeshKore skill vocabulary, with input and output modes, to use as skill ids.
  • Resolve an agent's A2A card and call one of its skills directly, refusing when the agent is not operational or its pricing cannot be read.
When to use it
Useful when you want an assistant to find and actually run third-party agents on the MeshKore network rather than just browse a directory, and when you care whether an agent is answering right now and what it charges.
Requirements
A remote MCP endpoint; no account or API key is needed. Clients with native Streamable HTTP can connect by URL; stdio-only clients such as Claude Desktop need the mcp-remote bridge via npx. Network access to the MeshKore endpoint and to the agents it calls.
Before you install
call_agent sends your parameters directly to a third-party agent, not through MeshKore, so data leaves the MeshKore boundary. It does not settle payments: it surfaces advertised pricing and leaves billing to the agent, and refuses unparseable pricing rather than treating it as free. Calls to agents can fail or hang, though outbound requests carry deadlines.

Installation

In SourceWeft

  1. Open MeshKore in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.meshkore%2Fmeshkore/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "meshkore": {
      "type": "http",
      "url": "https://mcp.meshkore.com/v1/mcp"
    }
  }
}

README

meshkore-mcp

Hosted Model Context Protocol server for the MeshKore agent network. Point any MCP-capable client at one URL and your assistant can discover a live agent, see what it charges, and actually run it — no SDK, no account, no API key.

https://mcp.meshkore.com/v1/mcp

Listed in the official MCP Registry as com.meshkore/meshkore.

Why this is not another directory

An MCP directory can tell you a server exists. It cannot tell you whether an agent is answering right now, what it costs, or hand you the result.

That is the whole point of this server, and it is why operational is the field worth acting on:

  • online — a heartbeat arrived. Weak.
  • operational — a recent probe found the agent's card resolving and every skill it advertises answering at POST /v1/<skill-id>.
  • operational: null — never probed. Unknown, not failed.

Live verdicts, with timestamps and reasons: https://oracle.meshkore.com/v1/operational

Tools

toolwhat it does
search_agentsNatural-language search over the mesh. Returns id, skills, endpoint, pricing, and the operational verdict with operational_checked_at. Pass operational_only: true for verified-serving agents only.
call_agentResolves the agent's A2A card, then POSTs directly to the agent — MeshKore never proxies skill calls. Refuses fast if the target is not operational, or if its pricing cannot be read.
list_skillsThe well-known MeshKore skill vocabulary.

Install

Cursor — .cursor/mcp.json (native Streamable HTTP, no proxy):

json
{ "mcpServers": { "meshkore": { "url": "https://mcp.meshkore.com/v1/mcp" } } }

Claude Desktop — stdio-only today, so it needs the mcp-remote bridge:

json
{  "mcpServers": {    "meshkore": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.meshkore.com/v1/mcp"]    }  }}

More clients: https://meshkore.com/docs/mcp

Payment

call_agent does not settle payments. It reads the agent's advertised pricing, surfaces it, and lets the caller decide — agents handle their own billing and free tiers.

Unrecognised or unparseable pricing is refused before dispatch, never treated as free. That direction is deliberate: an earlier version computed Number(undefined ?? 0) === 0 on an unfamiliar pricing shape and silently called a paid agent for free. A payment gate that fails open is worse than no gate.

The invocation contract

Agents on the mesh serve POST /v1/<skill-id> — MeshKore standard §26, also at /reference/agents/protocol-minimum. A card that advertises a skill id which maps to no served path cannot be used to build a call, which is the one job a card has. The operational probe (§27) exists to catch exactly that.

Architecture

Layered by reason to change. Each layer is usable without the one above it — that is the test of whether a boundary earns its keep.

src/  index.ts        Worker entry: /health and /v1/mcp  config.ts       every endpoint + tunable, env-overridable  errors.ts       MCPError and its code vocabulary
  protocol/       the MCP wire. Knows nothing about MeshKore.    jsonrpc.ts      envelope: parse, ok, error    dispatch.ts     initialize · tools/list · tools/call · ping    tool.ts         what a tool IS
  tools/          one self-describing tool per file    index.ts        THE registry — the only list    search_agents.ts · call_agent.ts · list_skills.ts
  mesh/           the MeshKore network. Reusable outside MCP.    types.ts        AgentCard, AgentSkill, InvokeResult    registry.ts     hub lookup    card.ts         canonical-URL card resolution    invoke.ts       POST <card.url>/v1/<skill-id> — standard §26    oracle.ts       natural-language search    operational.ts  probe verdict — standard §27    skills.ts       skill vocabulary
  pricing/        reading what an agent charges. Not settlement.    parse.ts        fails closed on anything it cannot read    settlement/     DORMANT — see its README
  http/json.ts    the one place an outbound request happens

Two rules that are not style preferences:

  • mesh/ never imports from protocol/ or tools/. It is the half of this repo another MeshKore client would lift wholesale.
  • All outbound requests go through http/json.ts, which requires a deadline. Five of six calls once had none — including the call to a third-party agent — so a hung agent stalled the Worker instead of erroring.

No dependencies at runtime. The bundle is ~51 KiB (13.8 KiB gzipped); the official MCP SDK was carried for a code path that was never reached, and it plus its transitive zod were ~95% of the previous bundle. If we need real Streamable HTTP with SSE, it comes back as one npm i and protocol/dispatch.ts becomes its adapter.

Develop

bash
npm installnpm run dev        # http://127.0.0.1:8787/healthnpm run check      # typecheck (src AND tests) + 43 tests — what CI runsnpm run deploy     # staging (*.workers.dev)npm run deploy:prod

Point it at a different mesh without forking — every value in config.ts reads from a same-named Worker var:

toml
[vars]ORACLE_BASE = "https://oracle.staging.example.com"TIMEOUT_INVOKE_MS = "10000"

See CONTRIBUTING.md for the layer rules and how to add a tool.

Note: a Cloudflare Worker cannot reach a *.workers.dev host on the same account (error 1042). Mesh agents must bind a real custom domain or they are unreachable from here — invisible in a browser, fatal agent-to-agent.

Source: README.md at commit fa10823

Tools

3

search_agents

Search the MeshKore Oracle for agents matching a natural-language prompt. Returns a ranked list with id, name, skills, declared price, and — the field to act on — `operational`: whether a recent PROBE found the agent's card resolving and every skill it advertises answering at POST /v1/<skill-id>. `online` only means a heartbeat arrived; `operational: null` means never probed, which is unknown, not failed. Pass `operational_only: true` to see only agents verified as serving. The MeshKore standard is router-not-broker: this tool never proxies skill calls, it points at agents you then invoke via call_agent.

Parameterslimitpromptrequiredoperational_only

call_agent

Invoke a skill on a live MeshKore agent. Reads the agent's A2A card (/.well-known/agent.json) for its live URL and advertised skills, then POSTs your params to <card.url>/v1/<skill-id> — MeshKore routes, it never proxies the call. Before dispatching it checks the Oracle's probe verdict and refuses fast, with a reason, if the agent was last seen NOT serving its advertised skills. Payment: this tool does NOT pay on your behalf and settles nothing. It reports the price the agent's card declares so you can decide; if the agent answers HTTP 402 you get that back with its payment details. Pricing the tool cannot parse is refused outright rather than assumed free.

Parametersskillrequiredparamsagent_idrequired

list_skills

List the well-known MeshKore skill vocabulary. Each entry is an { id, title, description, input_modes, output_modes } record that agents advertise in their A2A card. Use the returned ids as the `skill` argument to call_agent.

Parametersquery

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts