https://mcp.onesource.io/mcp ↗
# @one-source/mcp Unified MCP server for [OneSource](https://docs.onesource.io) — 31 tools for blockchain data, live chain queries, and API documentation in a single server. Combines [`@one-source/api-mcp`](https://www.npmjs.com/package/@one-source/api-mcp) (22 tools) and [`@one-source/docs-mcp`](https://www.npmjs.com/package/@one-source/docs-mcp) (9 tools) so your AI assistant gets full access to OneSource with one MCP connection. > **What is MCP?** The [Model Context Protocol](https://modelcontextprotocol.io) lets AI assistants call tools and access data sources. This server exposes both the OneSource blockchain API and its documentation as tools. ## Quick Start ### Claude Code ```bash claude mcp add onesource -- npx @one-source/mcp ``` ### Claude Desktop / Cursor Add to your MCP config: ```json { "mcpServers": { "onesource": { "command": "npx", "args": ["-y", "@one-source/mcp"] } } } ``` ### Any MCP Client (stdio) ```bash npx @one-source/mcp ``` #
OneSource MCP is a remote MCP server published at mcp.onesource.io. It has been probed 6 times since 9/10/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 716 ms, a delay an agent will notice. It exposes a broad tool surface of 44 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
1s_contract_info_live — Description lacks specific use cases for detected standards1s_erc20_balance_live — Optional fields explanation is incomplete and ambiguous1s_ds_book — Name does not clearly indicate Deepstate order book functionality1s_tx_details_live — No explicit error handling documentation for invalid transaction queriesRisk: medium
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/one-source-mcp-1s)<a href="https://mcpmetrics.io/servers/one-source-mcp-1s"><img src="https://mcpmetrics.io/badge/one-source/mcp-1s/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-11 13:13:33 | Legacy | 400 | 751 | 200 | 730 | 2025-11-25 |
| 2026-09-11 11:20:19 | Legacy | 400 | 707 | 200 | 716 | 2025-11-25 |
| 2026-09-11 09:28:19 | Legacy | 400 | 730 | 200 | 715 | 2025-11-25 |
| 2026-09-11 07:35:54 | Legacy | 400 | 603 | 200 | 595 | 2025-11-25 |
| 2026-09-11 05:44:28 | Legacy | 400 | 933 | 200 | 916 | 2025-11-25 |
| 2026-09-10 21:16:35 | Auth-gated | 401 | 388 | 401 | 343 | — |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.