# BTCDecoded Intelligence (remote · mcp.btcdecoded.org)

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

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.btcdecoded.org`: 70/100 (this document), [markdown](https://verifymcp.io/servers/org-btcdecoded-intelligence/mcp.md), [page](https://verifymcp.io/servers/org-btcdecoded-intelligence/mcp)

## Channel facts

- Endpoint: `https://mcp.btcdecoded.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 78/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1542 tokens (~128/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the BTCDecoded Intelligence MCP server?

BTCDecoded Intelligence is a hosted endpoint at https://mcp.btcdecoded.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http org-btcdecoded-intelligence 'https://mcp.btcdecoded.org/mcp'
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "org-btcdecoded-intelligence": {
      "type": "http",
      "url": "https://mcp.btcdecoded.org/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.org-btcdecoded-intelligence]
url = "https://mcp.btcdecoded.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "org-btcdecoded-intelligence": {
      "type": "remote",
      "url": "https://mcp.btcdecoded.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add org-btcdecoded-intelligence --url 'https://mcp.btcdecoded.org/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  org-btcdecoded-intelligence:
    url: "https://mcp.btcdecoded.org/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "org-btcdecoded-intelligence": {
      "Transport": "http",
      "Url": "https://mcp.btcdecoded.org/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add org-btcdecoded-intelligence -t streamable-http -u 'https://mcp.btcdecoded.org/mcp'
```

### Other

```json
{
  "mcpServers": {
    "org-btcdecoded-intelligence": {
      "type": "http",
      "url": "https://mcp.btcdecoded.org/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 70, 0)

- [security] Tool “get_contributor_profile” rewrote its description, which is the text the model reads
- [security] Tool “search” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “analyze_submission”
- [cosmetic] “get_contributor_profile” reworded the description of “login”

### 2026-09-19 (score 70, +39)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-09-17 (score 31)

First indexed and scored.

## MCP tools (12)

### `search` (~437 tokens)

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 precursor papers (source=articles); 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, Lightning BOLTs, Mastering Taproot, bitcoin.org developer docs and RPC reference, Optech topics/newsletters); Nostr NIPs (source=nips); Stratum V2 spec (source=sv2); BLIPs, LNURL LUDs, and LSP spec (source=ln-spec); BDK, HWI, LDK, LND/CLN, miniscript, Sparrow Wallet docs (source=tooling); specs, maps, research, and topic syntheses (source=synthesis).

Input parameters:

- `query` (string, required): Natural-language question or topic to retrieve cited passages for.
- `source` (string): Optional pin to one corpus source (e.g. github, irc, mail, price, textbooks). Omit to search both layers.
- `when` (string): Optional date pin YYYY, YYYY-MM, or YYYY-MM-DD. Keeps cites whose passage date starts with that prefix. Undated cites drop.

### `assess_argument` (~81 tokens)

Match the claim to a discourse game, then the documented counter-move, from Bitcoin_Discourse_Games or Bitcoin_Governance_Complete_Argument_Map. Return pattern + cites. No new synthesis. These files are product policy (internal), not contemporaneous evidence.

Input parameters:

- `text` (string, required): Claim or thread excerpt to match against the documented discourse games.

### `get_contributor_profile` (~82 tokens)

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.

Input parameters:

- `login` (string, required): GitHub login or unique public GitHub name, case-insensitive. Unknown values return found=false.

### `get_passage` (~93 tokens)

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.

Input parameters:

- `doc` (string): Document id when id is omitted (with source).
- `id` (string): Vectorize id from a search cite.
- `source` (string): Corpus source when id is omitted (with doc).

### `verify_claim` (~134 tokens)

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.

Input parameters:

- `claim` (string, required): Claim to score against the stored excerpt.
- `doc` (string): Document id when id is omitted (with source).
- `id` (string): Vectorize id from a search cite.
- `source` (string): Corpus source when id is omitted (with doc).

### `analyze_pr` (~93 tokens)

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.

Input parameters:

- `ref` (string): Alternate to url: owner/repo#n.
- `url` (string): Public GitHub pull request URL (https://github.com/owner/repo/pull/n).

### `analyze_issue` (~86 tokens)

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.

Input parameters:

- `ref` (string): Alternate to url: owner/repo/issues/n.
- `url` (string): Public GitHub issue URL (https://github.com/owner/repo/issues/n).

### `analyze_submission` (~263 tokens)

Advisory spec-versus-submission check. Retrieves cited index passages, then a closed judge label: met, not_met, or ambiguous. Empty index pack is ambiguous. Optional public GitHub PR (github_pr) is packed; private repos fail. Not a merge, payout, or money check. Does not post comments.

Input parameters:

- `caller_ref` (string): Optional opaque correlation id. Echoed, not interpreted.
- `github_pr` (string): 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` (array): Optional named criteria strings. When present, the judge may score each 0-1 from the cite pack.
- `source` (string): Optional pin to one corpus source (e.g. github, irc, mail, spec). Omit to search both layers.
- `spec` (string, required): Natural-language spec or acceptance criteria to check against.
- `submission` (string, required): Natural-language submission text (description and/or public PR pack).
- `when` (string): Optional date pin YYYY, YYYY-MM, or YYYY-MM-DD. Keeps cites whose passage date starts with that prefix.

### `find_discourse` (~93 tokens)

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

Input parameters:

- `path` (string, required): Source path to search (e.g. src/validation.cpp).
- `query` (string): Optional extra search text.
- `repo` (string): Optional owner/repo token to include in the query.
- `symbol` (string): Optional function or type name.

### `find_precedent` (~64 tokens)

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.

Input parameters:

- `query` (string, required): Proposal title, BIP number, or change description.

### `find_incident` (~59 tokens)

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.

Input parameters:

- `query` (string, required): CVE id or incident name.

### `find_spec_impl` (~57 tokens)

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

Input parameters:

- `query` (string, required): Spec section, rule, or implementation question.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-btcdecoded-intelligence/mcp#diagnostics

## Score history

- 2026-09-20: 70
- 2026-09-19: 70
- 2026-09-18: 31
- 2026-09-17: 31

## Common questions

### What is the BTCDecoded Intelligence MCP server?

BTCDecoded Intelligence is an MCP server listed in the public MCP registry as org.btcdecoded/intelligence. Cited Bitcoin coordination record search (~783k). Lightning. MCP. Not prices/chain analytics. This page covers its hosted endpoint (https://mcp.btcdecoded.org/mcp).

### Is the BTCDecoded Intelligence MCP server safe to use?

BTCDecoded Intelligence scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the BTCDecoded Intelligence MCP server expose?

BTCDecoded Intelligence exposes 12 tools: search, assess_argument, get_contributor_profile, get_passage, verify_claim, and 7 more. Their descriptions and schemas cost roughly 1,542 tokens of context every time the server is loaded.

### Does the BTCDecoded Intelligence MCP server require authentication?

Yes. BTCDecoded Intelligence asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the BTCDecoded Intelligence MCP server still maintained?

BTCDecoded Intelligence is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.btcdecoded.org/mcp
- Website: https://btcdecoded.org/intelligence/
- Changelog RSS feed: https://verifymcp.io/servers/org-btcdecoded-intelligence/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/org-btcdecoded-intelligence/mcp.json
- HTML version of this page: https://verifymcp.io/servers/org-btcdecoded-intelligence/mcp