web3-docs
Unifies 11 protocol specification repositories (EIPs, BIPs, CIPs, etc.) and canonical contract addresses across 10 chains into a local FTS5 index, enabling coding agents to retrieve exact spec text and contract addresses via natural language queries.
README
<!-- mcp-name: io.github.dioptx/web3-docs -->
<div align="center">
web3-docs
One MCP server, eleven protocol-spec repos. Ask your coding agent about EIPs, BIPs, ADRs, CIPs, RFCs and canonical contract addresses — without ever leaving your editor. Works with any MCP-compatible client: Claude Code, Cursor, Windsurf, Cline, Zed, Continue, OpenCode, Codex, and more.

<sub>Or replay in your own terminal: <code>asciinema play <a href="docs/assets/demo.cast">docs/assets/demo.cast</a></code></sub>
</div>
Why
Specs for blockchain protocols live across eleven different upstream repos on three different forges. Every time you need to look up EIP-4844, BIP-340, CIP-25, or which fork shipped PUSH0, you're tab-hunting through GitHub. This MCP indexes them all locally with FTS5 ranking — 1,767 proposals across 10 chains plus addresses for 19 protocols on Ethereum, Arbitrum, Base, Optimism, Polygon, and more — so your agent answers with the actual spec text, not a hallucinated paraphrase.
Install
Requires: Python 3.11+ ·
uv(providesuvx) · ~500 MB free disk for the index ·giton PATH (used by--sync).
Step 1 — build the index (one-time, ~2 min, ~500 MB in ~/.cache/web3-docs-mcp/)
uvx web3-docs-mcp --sync
Step 2 — register the server with your agent
The launch command is identical across clients:
uvx web3-docs-mcp
<details><summary><b>Claude Code</b></summary>
claude mcp add web3-docs -- uvx web3-docs-mcp
</details>
<details><summary><b>Cursor · Windsurf · Cline · Continue · Zed · generic stdio MCP client</b></summary>
Add to the client's MCP config (~/.cursor/mcp.json, ~/.codeium/windsurf/mcp_config.json, cline_mcp_settings.json, the mcpServers block in your Zed settings.json, etc.):
{
"mcpServers": {
"web3-docs": {
"command": "uvx",
"args": ["web3-docs-mcp"]
}
}
}
</details>
<details><summary><b>OpenAI Codex CLI</b></summary>
codex mcp add web3-docs -- uvx web3-docs-mcp
</details>
<details><summary><b>pip / pipx</b></summary>
pip install web3-docs-mcp
# or:
pipx install web3-docs-mcp
</details>
<details><summary><b>From source (development)</b></summary>
git clone https://github.com/dioptx/web3-docs.git && cd web3-docs
uv sync
uv run python server.py --sync # build index
uv run python server.py # run stdio server
</details>
Restart your agent, then try "Use web3-docs to look up EIP-1559."
What you can ask
| Ask your agent… | Tool chain |
|---|---|
| "What's the fee market in EIP-4844?" | resolve_proposal → query_protocol_docs(query="fee") |
| "Show me Cosmos ADR-001." | resolve_proposal → query_protocol_docs |
| "What's in Cancun?" | list_fork_proposals("Cancun") |
| "Which BIPs activated with Taproot?" | list_fork_proposals("Taproot") |
| "Uniswap router on Base?" | resolve_contract(protocol="uniswap", chain_id="8453") |
| "Cardano CIP for native tokens?" | resolve_proposal("native tokens", chain="cardano") → cip-25 |
| "ERC-4337 EntryPoint address on Arbitrum?" | resolve_contract("erc4337", "42161") |
| "Staking on Cosmos vs Polkadot?" | resolve_proposal("staking", chain="cosmos") then chain="polkadot" |
<div align="center">

<sub>Multi-chain canonical addresses, no etherscan tabs.</sub>
</div>
Tools
| Tool | What it does |
|---|---|
resolve_proposal(query, chain?) |
Fuzzy-find a proposal by keyword, fork name, opcode, or ID. Returns top-5 ranked hits with chain/status/fork. Pass chain= (ethereum, bitcoin, cosmos, …) to disambiguate when keywords match multiple chains. |
query_protocol_docs(proposal_id, query?) |
Read the full spec body. With query, returns only the most relevant sections (token-budgeted). Includes metadata header (status, fork, activation date, authors). |
list_fork_proposals(fork_name) |
List every proposal activated by a named fork. Answers "what's in Cancun?" / "BIPs activated with Taproot?". Handles aliases (Pectra → Prague, Dencun → Cancun, Shapella → Shanghai, The Merge → Paris). |
resolve_contract(protocol, chain_id?) |
Look up canonical deployed addresses. 19 protocols × major EVM chains. Omit chain_id for all chains. |
<div align="center">

<sub>Fork → all proposals it shipped, then drill into one. Two tool calls instead of an afternoon of tab-hunting.</sub>
</div>
Sources
11 upstream repos, all synced via --sync:
| Chain | Source |
|---|---|
| Ethereum (EIPs) | ethereum/EIPs |
| Ethereum (ERCs) | ethereum/ERCs |
| Bitcoin | bitcoin/bips |
| Solana | solana-foundation/solana-improvement-documents |
| Cosmos | cosmos/cosmos-sdk (docs/architecture) |
| Polkadot | polkadot-fellows/RFCs |
| Stacks | stacksgov/sips |
| Avalanche | avalanche-foundation/ACPs |
| Cardano | cardano-foundation/CIPs |
| Tezos | tezos/tzip |
| Sui | sui-foundation/sips |
Fork mappings come from ethereum/execution-specs plus canonical Bitcoin soft-fork activations (P2SH, SegWit, Taproot, …).
Contract registry covers: aave, across, chainlink, compound, create2_deployer, curve, ens, erc4337, gnosis_safe, lido, maker, multicall, oneinch, permit2, seaport, uniswap, usdc, usdt, weth.
Why not …
…just gh search or WebFetch each spec on demand? You'd burn tokens on HTML markup and pay a network round-trip per query. web3-docs indexes everything once into local SQLite + FTS5 — sub-millisecond ranked search, plain-text bodies, no rate limits, works offline.
…one MCP per chain? You'd manage eleven separate servers and your agent wouldn't know which to call. One unified tool with a single resolve_proposal entry point lets the model find the right doc by concept (e.g. "blob transactions" → eip-4844) rather than guessing the source.
…ask the model directly without an MCP? Models hallucinate spec details — wrong fork, wrong gas costs, wrong opcode numbers. This server returns the actual upstream text with metadata (status, fork, activation date) so the agent can quote it verbatim.
…use a vector DB? Spec corpora are small (≈ 1.7K docs), domain vocabulary is precise (PUSH0, BLOBHASH, taproot), and exact-term matching beats embeddings here. FTS5 gives BM25 ranking with zero infrastructure.
Configuration
| Env var | Default | Purpose |
|---|---|---|
WEB3_DOCS_DATA_DIR |
~/.cache/web3-docs-mcp (macOS/Linux) |
Where source repos and the SQLite index live |
Troubleshooting
"Index is empty" on any tool call. You haven't run --sync yet. Run:
uvx web3-docs-mcp --sync
uvx: command not found. Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh.
Want to free disk space? Source repos (~/.cache/web3-docs-mcp/repos/) can be deleted after sync; only proposals.db is needed at runtime. Re-run --sync to update.
Stale data? Re-run --sync — it does a fast git pull and reindexes incrementally.
Development
git clone https://github.com/dioptx/web3-docs.git && cd web3-docs
uv sync --extra test
uv run pytest # 98 tests, BDD + unit
uv build # build wheel + sdist
Status
v0.2.0 — adds Cardano CIPs, Tezos TZIPs, Sui SIPs (10 chains, 1,767 proposals). SQLite + FTS5, FastMCP stdio transport. See CHANGELOG.md for release history.
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。