MCP MeasureMCP Measure

索引已观测

BTCDecoded Intelligence

Cited Bitcoin coordination record search (~783k). Lightning. MCP. Not prices/chain analytics.

我该使用它吗

质量与安全性

A
描述质量
93%
模式完整度
98%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现（1）

  • LOWTool 'assess_argument' description lacks action verb在 assess_argument 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~2,820token 数（工具定义）
~1.3 KB典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 2.20%）

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中：

{
  "mcpServers": {
    "intelligence": {
      "url": "https://mcp.btcdecoded.org/mcp"
    }
  }
}

远程端点

https://mcp.btcdecoded.org/mcpstreamable-http

它能做什么

工具清单

工具（13）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search(query, source, when, snapshot)

Cited Bitcoin coordination index. Not a live quote, ETF, derivatives, or chain analytics. Pin a layer with source. If ok is false, the index has no passage. Every plan searches both layers. Footnotes label domain (protocol, lightning, mining, tooling, security, nostr, governance). Record: IRC review logs, bitcoin-dev and cryptography mailing lists, GitHub PRs/issues/commits, Delving Bitcoin, Bitcointalk, Satoshi communications, BIP text and BIP PRs/issues, release tags/signers, and Bitcoin Core source (consensus, policy, script, validation, net, mempool, miner). Price: CoinMetrics community PriceUSD (source=price), every daily close from 2010-07-18 through the last dated row, packed by ISO week. Curated: named primary texts (source=articles); SatoshiLabs SLIPs (source=slips); academic protocol/security papers (source=papers); open textbooks (source=textbooks: Learning Bitcoin from the Command Line, Karasavvas, minium, Elementary Bitcoin, Dorier C#, Book of Bitcoin commentary, Mastering Bitcoin 2e, Mastering Bitcoin 3e, Mastering LN, Mastering Taproot, bitcoin.org developer docs and RPC reference, Optech topics/newsletters); Nostr NIPs (source=nips); Stratum V2 spec (source=sv2); Lightning BOLTs, BLIPs, LNURL LUDs, and LSP spec (source=ln-spec); BDK, HWI, LDK, LND/CLN, miniscript, Sparrow Wallet docs (source=tooling); SeedSigner, Bitkey, and Foundation Passport docs (source=hw); specs, maps, research, and topic syntheses (source=synthesis).

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Natural-language question or topic to retrieve cited passages for."
    },
    "source": {
      "type": "string",
      "enum": [
        "corpus",
        "findings",
        "spec",
        "book",
        "maintainers",
        "secsov",
        "commons-whitepaper",
        "bitcoin-whitepaper",
        "articles",
        "papers",
        "textbooks",
        "nips",
        "slips",
        "sv2",
        "ln-spec",
        "tooling",
        "hw",
        "synthesis",
        "blvm-docs",
        "pool",
        "vision",
        "governance",
        "github",
        "irc",
        "mail",
        "delving",
        "bitcointalk",
        "core_src",
        "src",
        "satoshi",
        "releases",
        "bips",
        "price"
      ],
      "description": "Optional pin to one corpus source (e.g. github, irc, mail, price, textbooks). Omit to search both layers."
    },
    "when": {
      "type": "string",
      "description": "Optional date pin YYYY, YYYY-MM, or YYYY-MM-DD. Keeps cites whose passage date starts with that prefix. Undated cites drop."
    },
    "snapshot": {
      "type": "boolean",
      "description": "If true, persist this result as a dated snapshot."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢assess_argument(text)

Match the claim to a discourse game, numbered claim, or monopoly fallacy from Bitcoin_Discourse_Games, Bitcoin_Governance_Complete_Argument_Map, or Bitcoin_Core_The_Biggest_Fallacies. Return kind + heading pattern + cites. No new synthesis. These files are product policy (internal), not contemporaneous evidence.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Claim or thread excerpt to match against the documented discourse games."
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}
🟢get_contributor_profile(login)

Public-record facts for a GitHub login, or that login's unique public GitHub name, from research findings. Known set is small (canonical maintainers). Most logins return found=false. Do not invent employment or affiliation.

输入模式

{
  "type": "object",
  "properties": {
    "login": {
      "type": "string",
      "description": "GitHub login or unique public GitHub name, case-insensitive. Unknown values return found=false."
    }
  },
  "required": [
    "login"
  ],
  "additionalProperties": false
}
🟢get_passage(id, source, doc, uri)

Return the stored index passage for a search cite. Pass id from the cite, or source plus doc. Not a live web fetch. If ok is false, the index has no passage.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Vectorize id from a search cite."
    },
    "source": {
      "type": "string",
      "description": "Corpus source when id is omitted (with doc)."
    },
    "doc": {
      "type": "string",
      "description": "Document id when id is omitted (with source)."
    },
    "uri": {
      "type": "string",
      "description": "intel:// locator from a cite. Preferred over id when present."
    }
  },
  "additionalProperties": false
}
🟢get_snapshot(id)

Replay a stored dated report. Free. Does not re-search or re-judge. A new as_of is a new call of the original tool.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "snapshot_id from a prior tool result."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢verify_claim(claim, id, source, doc)

Score whether a stored index passage supports a claim. Pass id from a search cite, or source plus doc. Loads the stored excerpt then returns noul 0-1, skipped if the judge is unavailable, or no_passage if the index has no excerpt. Not a live web fetch. The judge is not a source.

输入模式

{
  "type": "object",
  "properties": {
    "claim": {
      "type": "string",
      "description": "Claim to score against the stored excerpt."
    },
    "id": {
      "type": "string",
      "description": "Vectorize id from a search cite."
    },
    "source": {
      "type": "string",
      "description": "Corpus source when id is omitted (with doc)."
    },
    "doc": {
      "type": "string",
      "description": "Document id when id is omitted (with source)."
    }
  },
  "required": [
    "claim"
  ],
  "additionalProperties": false
}
🟢analyze_pr(url, ref)

PR review scaffold for a public GitHub PR. Fetches filenames and a 4000-char patch pack, plus a capped live thread. Private repos fail. Precedent from the index. Does not post comments.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public GitHub pull request URL (https://github.com/owner/repo/pull/n)."
    },
    "ref": {
      "type": "string",
      "description": "Alternate to url: owner/repo#n."
    }
  },
  "additionalProperties": false
}
🟢analyze_issue(url, ref)

Issue review scaffold for a public GitHub issue. Live-fetches title, body, and a capped comment thread. Private repos fail. Precedent from the index. Does not post comments.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public GitHub issue URL (https://github.com/owner/repo/issues/n)."
    },
    "ref": {
      "type": "string",
      "description": "Alternate to url: owner/repo/issues/n."
    }
  },
  "additionalProperties": false
}
🟢analyze_submission(spec, submission, source, when, github_pr, ...)

Advisory spec-versus-submission check. Retrieves cited index passages, then a closed judge label: met, not_met, or ambiguous. Empty or off-topic cite packs are ambiguous. Scores a named requirement only when a packed cite bears on it. structuredContent.rationale names met, unmet, and unaddressed requirements without pasting excerpts. Optional public GitHub PR (github_pr) is packed; private repos fail. Not a merge, payout, or money check. Does not post comments.

输入模式

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "description": "Natural-language spec or acceptance criteria to check against."
    },
    "submission": {
      "type": "string",
      "description": "Natural-language submission text (description and/or public PR pack)."
    },
    "source": {
      "type": "string",
      "enum": [
        "corpus",
        "findings",
        "spec",
        "book",
        "maintainers",
        "secsov",
        "commons-whitepaper",
        "bitcoin-whitepaper",
        "articles",
        "papers",
        "textbooks",
        "nips",
        "slips",
        "sv2",
        "ln-spec",
        "tooling",
        "hw",
        "synthesis",
        "blvm-docs",
        "pool",
        "vision",
        "governance",
        "github",
        "irc",
        "mail",
        "delving",
        "bitcointalk",
        "core_src",
        "src",
        "satoshi",
        "releases",
        "bips",
        "price"
      ],
      "description": "Optional pin to one corpus source (e.g. github, irc, mail, spec). Omit to search both layers."
    },
    "when": {
      "type": "string",
      "description": "Optional date pin YYYY, YYYY-MM, or YYYY-MM-DD. Keeps cites whose passage date starts with that prefix."
    },
    "github_pr": {
      "type": "string",
      "description": "Optional public GitHub PR URL (https://github.com/owner/repo/pull/n) or ref (owner/repo#n). Packed into the submission. Private repos fail. Not an arbitrary URL fetch."
    },
    "requirements": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional named criteria strings. When present, the judge scores a criterion 0-1 only if packed cites bear on it; otherwise the score is omitted."
    },
    "caller_ref": {
      "type": "string",
      "description": "Optional opaque correlation id. Echoed, not interpreted."
    }
  },
  "required": [
    "spec",
    "submission"
  ],
  "additionalProperties": false
}
🟢find_discourse(path, repo, symbol, query, snapshot)

Retrieve GitHub, mail, IRC, and Delving cites for a path or symbol. Mail/IRC rarely include paths.

输入模式

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "Source path to search (e.g. src/validation.cpp)."
    },
    "repo": {
      "type": "string",
      "description": "Optional owner/repo token to include in the query."
    },
    "symbol": {
      "type": "string",
      "description": "Optional function or type name."
    },
    "query": {
      "type": "string",
      "description": "Optional extra search text."
    },
    "snapshot": {
      "type": "boolean",
      "description": "If true, persist this result as a dated snapshot."
    }
  },
  "required": [
    "path"
  ],
  "additionalProperties": false
}
🟢find_precedent(query, snapshot)

Retrieve BIP, GitHub, and mail cites for a proposal. Disposition is only what a cite heading or URL already says. Does not invent merged/rejected/stalled labels.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Proposal title, BIP number, or change description."
    },
    "snapshot": {
      "type": "boolean",
      "description": "If true, persist this result as a dated snapshot."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢find_incident(query, snapshot)

Retrieve index cites for a named incident or CVE (e.g. CVE-2018-17144). Same search page as search. Empty if the index has no passage.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "CVE id or incident name."
    },
    "snapshot": {
      "type": "boolean",
      "description": "If true, persist this result as a dated snapshot."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢find_spec_impl(query, snapshot)

Retrieve spec, Core source, and GitHub cites for a spec section or behavior. Cites only. Does not emit aligned/gap/divergence verdicts.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Spec section, rule, or implementation question."
    },
    "snapshot": {
      "type": "boolean",
      "description": "If true, persist this result as a dated snapshot."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

推荐提示词

search_research
Search for information about [topic] using BTCDecoded Intelligence
预期工具： search
find_specific
Find [specific item] using BTCDecoded Intelligence
预期工具： search
retrieve_data
Get details about [item] from BTCDecoded Intelligence
预期工具： get_contributor_profile
fetch_info
Fetch [information type] using BTCDecoded Intelligence
预期工具： get_contributor_profile
research_workflow
Search for [topic], then get detailed information about the top results using BTCDecoded Intelligence
预期工具： searchget_contributor_profile

社区

评价此服务器

证据

最近观测

已验证未记录版本13 个工具
已验证未记录版本13 个工具