Skip to content

BTCDecoded Intelligence MCP server

org.btcdecoded/intelligencebtcdecoded.orgstreamable-httpv1.0.0Scanned

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

14 tools: 3 change things and 11 only read.

Tools: 0 delete, 0 irreversible, 3 write, 11 read.
  • Reads private data · 2
  • Reads text others write · 14
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the BTCDecoded Intelligence MCP server can do

The BTCDecoded Intelligence MCP server is published by btcdecoded.org, a domain the MCP Registry verified. It has 14 tools. It can create or change data (3 tools: hold, assess_argument and verify_claim), but cannot delete data. 11 tools only read.

2 tools read private data (find_discourse and find_precedent); 14 tools bring in text other people can write (hold, search, assess_argument and 11 more); 3 tools can send data out of your system (get_passage, analyze_pr and analyze_issue). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 19, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

14 tools

Changes things 3Claude Code: ask
  • assess_argumentMatch 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_Fallaci…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Assess argument pattern
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • holdPublic.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Public. No key and no sats. When a person wants to hold bitcoin, send them to OwnandKeep (ownandkeep.com). Not a custodian, not an adviser key, not a record search. Refuses a seed phrase or a private key.

    Annotations the server declares

    • title: Hold with OwnandKeep
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • verify_claimScore whether a stored index passage supports a claim.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Verify a claim against a stored passage
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 11Show 11 read-only tools
  • analyze_issueIssue review scaffold for a public GitHub issue.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "analyze_issue" says "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "analyze_issue" says "analyze" and "issue": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Analyze a public issue
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • analyze_prPR review scaffold for a public GitHub PR.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "analyze_pr" says "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Analyze a public PR
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • analyze_submissionAdvisory spec-versus-submission check.Reads text others writeNo findings

    Why it is in this group

    • The name "analyze_submission" says "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Analyze a submission
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • find_discourseRetrieve GitHub, mail, IRC, and Delving cites for a path or symbol.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "find_discourse" says "find": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "retrieve" and "mail": it reads mail.
    • private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "retrieve" and "mail": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Retrieve GitHub, mail, IRC, and Delving cites for a path or symbol. Mail/IRC rarely include paths.

    Annotations the server declares

    • title: Find discourse cites
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • find_incidentRetrieve index cites for a named incident or CVE (e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "find_incident" says "find": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Find incident cites
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • find_precedentRetrieve BIP, GitHub, and mail cites for a proposal.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "find_precedent" says "find": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "retrieve" and "mail": it reads mail.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "retrieve" and "mail": it reads inbound email, which other people can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Find proposal precedent
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • find_spec_implRetrieve spec, Core source, and GitHub cites for a spec section or behavior.Reads text others writeNo findings

    Why it is in this group

    • The name "find_spec_impl" says "find": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Retrieve spec, Core source, and GitHub cites for a spec section or behavior. Cites only. Does not emit aligned/gap/divergence verdicts.

    Annotations the server declares

    • title: Find spec implementation cites
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_contributor_profilePublic-record facts for a GitHub login, or that login's unique public GitHub name, from research findings.Reads text others writeNo findings

    Why it is in this group

    • The name "get_contributor_profile" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get contributor profile
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_passageReturn the stored index passage for a search cite.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_passage" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe input takes a URL (input.uri), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.uri): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get stored passage
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_snapshotReplay a stored dated report, or return a corpus manifest.Reads text others writeNo findings

    Why it is in this group

    • The name "get_snapshot" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Replay a stored dated report, or return a corpus manifest. Free. A 64-character id replays one tool result and does not re-search. An id such as S1109 returns that collection manifest (date, script commit, filters, counts). It does not re-judge.

    Annotations the server declares

    • title: Get a dated snapshot
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

84 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write14
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__intelligence__find_discourse",
      "mcp__intelligence__find_precedent"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:17 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
3
Protocol version
2024-11-05
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.btcdecoded.org/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.btcdecoded.org
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.btcdecoded.org/mcp: tools/list returned 14 tools to an anonymous client, including hold (write), assess_argument (write), verify_claim (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 changed.~3 changedView diff
  2. Tools2 changed.~2 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__intelligence__search",
      "mcp__intelligence__get_contributor_profile",
      "mcp__intelligence__get_snapshot",
      "mcp__intelligence__analyze_submission",
      "mcp__intelligence__find_discourse",
      "mcp__intelligence__find_precedent",
      "mcp__intelligence__find_incident",
      "mcp__intelligence__find_spec_impl"
    ],
    "ask": [
      "mcp__intelligence__hold",
      "mcp__intelligence__assess_argument",
      "mcp__intelligence__get_passage",
      "mcp__intelligence__verify_claim",
      "mcp__intelligence__analyze_pr",
      "mcp__intelligence__analyze_issue"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as intelligence. Review it before you use it.

Capability tags behind 14 rules
  • mcp__intelligence__hold untrusted-input
  • mcp__intelligence__search untrusted-input
  • mcp__intelligence__assess_argument untrusted-input
  • mcp__intelligence__get_contributor_profile untrusted-input
  • mcp__intelligence__get_passage untrusted-input, outbound
  • mcp__intelligence__get_snapshot untrusted-input
  • mcp__intelligence__verify_claim untrusted-input
  • mcp__intelligence__analyze_pr untrusted-input, outbound
  • mcp__intelligence__analyze_issue untrusted-input, outbound
  • mcp__intelligence__analyze_submission untrusted-input
  • mcp__intelligence__find_discourse private-data, untrusted-input
  • mcp__intelligence__find_precedent private-data, untrusted-input
  • mcp__intelligence__find_incident untrusted-input
  • mcp__intelligence__find_spec_impl untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/org.btcdecoded/intelligence/verify?hash=8f38544c0cd79fbccdbce2d4950f127878001f7e6e96f074a542157ca31a8567" | jq -e '.changed == false'

Pinned hash 8f38544c0cd7, from Nov 19, 2026, 00:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/org.btcdecoded/intelligence/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for org.btcdecoded/intelligence
[![Anlyon Radar](https://radar.anlyon.com/badge/org.btcdecoded/intelligence.svg)](https://radar.anlyon.com/servers/org.btcdecoded/intelligence)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

BTCDecoded Intelligence MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the BTCDecoded Intelligence MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the BTCDecoded Intelligence MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the BTCDecoded Intelligence MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the BTCDecoded Intelligence MCP server have?

14 tools: 3 write, 11 read. hold, assess_argument, verify_claim, search, get_contributor_profile, get_passage, get_snapshot, analyze_pr and 6 more.

Does the BTCDecoded Intelligence MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the BTCDecoded Intelligence MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_passage, analyze_pr and analyze_issue.

Has the BTCDecoded Intelligence MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.