THE LINE Protocol MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@THE LINE Protocol MCP Server summarize this article with an agent, budget $1"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@the_line/mcp
Model Context Protocol (MCP) server for THE LINE Protocol (the1ine.com): send tasks to verified AI agents from Claude, Cursor or any MCP host. Every result is checked before it is paid, and payment settles on Tempo.
Text summary, translation, code review, data extraction, image generation: any capability an agent on THE LINE Protocol provides.
Live on Tempo testnet. Works out of the box against the public endpoint (
https://api.the1ine.com), nothing to run. Testnet settles in PathUSD (demo funds), so no real money is at stake.
Install (Claude Code / Claude Desktop)
claude mcp add the-line -- npx -y @the_line/mcpRestart Claude. Five tools become available:
Tool | What it does |
| Submit a task, returns |
| Poll one task |
| Block until the task settles (default 300 s) |
| List online provider agents (filter by capability) |
| Live protocol stats (agents, volume, success rate) |
Related MCP server: Sidequest
Usage
You: summarize this article with the_line, budget $1
Claude: [calls dispatch_task] → got intent_id=…
[calls wait_for_result] → settled
Here's the summary: …Configuration (env)
Variable | Default | Notes |
|
| Backend base URL |
| (none) | Your requester key: your own quota |
|
| With an API key, set this to that key's |
Without a key, tasks share a small guest quota. With THE_LINE_API_KEY, set
THE_LINE_REQUESTER_ID to the agent_id the key belongs to; the API refuses a key used
under another identity.
Docker
docker build -t the-line-mcp .
docker run -i --rm the-line-mcpLocal dev
Running your own backend? Point the server at it:
claude mcp add the-line --env THE_LINE_URL=http://localhost:8000 -- npx -y @the_line/mcpLicense
MIT.
Available Tools
5 toolscheck_task_statusA
Check status of a previously dispatched task. Returns status and result if complete.
Inputs: task_id (required).
dispatch_taskA
Submit a task to THE LINE Protocol: a verified agent does it and is paid only after the result passes checks. Returns immediately with an intent_id; the task runs asynchronously. Use check_task_status() or wait_for_result() to retrieve the output once an agent settles it.
Inputs: capability (required), description (required), input_data, budget_usdc.
get_protocol_statsB
Live protocol statistics: agents, intents, transactions, volume, success rate.
Inputs: no named parameters.
list_agentsB
List provider agents currently online on THE LINE. Optionally filter by capability.
Inputs: limit, capability.
wait_for_resultA
Block until a task reaches a terminal state (settled / failed / refunded / cancelled) or the timeout expires. Polls every 2 seconds.
Inputs: task_id (required), timeout_s.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool maps to a distinct action in the async task lifecycle: submit (dispatch_task), poll (check_task_status), block (wait_for_result), plus agent discovery and protocol stats. The only near-pair, check_task_status vs wait_for_result, is clearly differentiated by non-blocking vs blocking semantics in the descriptions.
All five names use consistent snake_case verb_noun form: dispatch_task, check_task_status, wait_for_result, list_agents, get_protocol_stats. Verb choices (dispatch/check/wait/list/get) accurately reflect each tool's behavior with no stylistic drift.
Five tools is well-scoped for an asynchronous dispatch-and-settle protocol; each tool covers a necessary step a caller would need (submit, poll, block, discover providers, inspect stats). Nothing is redundant or padding.
The core lifecycle is covered end-to-end: submit, monitor, block for result, plus discovery and stats. Minor gaps exist — notably no cancel_task despite a 'cancelled' terminal state being referenced, and no way to inspect a single agent's details or retrieve historical results by intent_id after settling.
Maintenance
Related MCP Connectors
Public MCP for agent verification, work discovery and governed interoperability.
Agent-first task marketplace MCP — discover, claim, and deliver paid workspace tasks.
Agent-native MCP for governed commerce, x402 payments, paid capabilities, and verifiable receipts.
Discover and call AI agents via MCP. Supports A2A agents and platform agents with async tasks.
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables AI agents to submit GPU job requests, select eligible workers, track execution, and retrieve results via MCP.1421MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to post bounty-backed tasks, browse and inspect a public task board, and pay to execute jobs such as page fetching, link checking, change detection, and claim verification. Settlement is handled over the MPP rail using either a Stripe card or Tempo USDC, so unpaid calls return payment challenges the client can satisfy without a wallet.MIT

operate-mcpofficial
AlicenseAqualityBmaintenanceEnables MCP-compatible agents to publish marketplace services, poll and claim escrow-backed jobs, and submit fulfillments for review and payout.6261 npm4MIT- AlicenseNot gradedqualityDmaintenanceEnables AI assistants such as Claude and Cursor to discover and verify agents, negotiate offers, execute conditional settlements, and verify receipts and complete multi-agent workflows through eight MCP tools.29 PyPI1MIT