Skip to content

Clairvoyance MCP server

fyi.clairvoyance/mcpclairvoyance.fyistreamable-httpv1.3.1Scanned

Software design skills for AI coding agents, inspired by A Philosophy of Software Design.

17 tools: 16 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 16 write, 1 read.
  • Reads private data · 1
  • Reads text others write · 0
  • Can send data out · 0
  • 6 findings

Tools listed without sign-in. Remote posture

With Anlyon

16 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 Clairvoyance MCP server can do

The Clairvoyance MCP server is published by clairvoyance.fyi, a domain the MCP Registry verified. It has 17 tools. It can create or change data (16 tools: deep-modules, module-boundaries, information-hiding, pull-complexity-down and 12 more), but cannot delete data. 1 tool only reads.

1 tool reads private data (fetch-reference).

The fixed checks matched 6 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 11, 2026, version 1.3.1.

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.

17 tools

Changes things 16Claude Code: ask
  • abstraction-qualityEvaluates whether abstractions provide a genuinely different way of thinking or are structurally shallow.1 finding

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "abstraction-quality" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Evaluates whether abstractions provide a genuinely different way of thinking or are structurally shallow. Use when adjacent layers feel redundant, wrappers add boilerplate without depth, or an abstraction feels leaky. Not for a single module's interface-to-implementation ratio (use deep-modules) or information leakage across boundaries (use information-hiding).

    Annotations the server declares

    • readOnlyHint: true
  • code-evolutionEvaluates whether changes to existing code maintain or degrade design quality.1 finding

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "code-evolution" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Evaluates whether changes to existing code maintain or degrade design quality. Use when the user asks to review a diff or PR (for example before merging it), or asks about recently modified files, to judge whether each change looks designed-in or bolted-on. Not for scanning design smells (use red-flags) or assessing overall design investment (use strategic-mindset).

    Annotations the server declares

    • readOnlyHint: true
  • comments-docsReviews comment quality and documentation practices: the four comment types, comments-first workflow, and comment rot.1 finding

    Why it is in this group

    • The name "comments-docs" says "comment": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "comments-docs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The name "comments-docs" says "comment": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Reviews comment quality and documentation practices: the four comment types, comments-first workflow, and comment rot. Use when reviewing comments or docs, when comments just repeat the code, or when something is hard to describe in a sentence. Not for naming or code obviousness (use naming-obviousness).

    Annotations the server declares

    • readOnlyHint: true
  • complexity-recognitionDiagnoses whether complexity exists and where it comes from, using the three-symptom, two-root-cause framework.No 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.
    Description, as the server wrote it
    Diagnoses whether complexity exists and where it comes from, using the three-symptom, two-root-cause framework. Use when code feels harder to work with than it should but the specific problem is unclear. Not for scanning known design smells (use red-flags) or evaluating a module's depth (use deep-modules).

    Annotations the server declares

    • readOnlyHint: true
  • deep-modulesMeasures module depth: whether the interface is simple relative to the implementation behind it.No 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.
    Description, as the server wrote it
    Measures module depth: whether the interface is simple relative to the implementation behind it. Use when an interface has too many parameters or methods, many small classes each do too little, or methods just forward calls. Not for whether adjacent layers provide different abstractions (use abstraction-quality) or merging/splitting modules (use module-boundaries).

    Annotations the server declares

    • readOnlyHint: true
  • design-it-twiceGenerates and compares at least two fundamentally different design alternatives on concrete criteria before committing.1 finding

    Why it is in this group

    • The description's first verb is "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "design-it-twice" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The description's first verb is "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Generates and compares at least two fundamentally different design alternatives on concrete criteria before committing. Use when the user asks to design something twice, or before committing to any significant design of classes, modules, APIs, or architecture. Also use when asked how to structure or architect a feature, or when writing the design or alternatives section of an RFC, design doc, or ADR. Not for judging strategic vs. tactical investment in existing code (use strategic-mindset) or whether a change degrades design (use code-evolution).

    Annotations the server declares

    • readOnlyHint: true
  • design-reviewOrchestrates a structured design review, running the other skills as a diagnostic funnel from complexity triage to a full red-flags sweep.No 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.
    Description, as the server wrote it
    Orchestrates a structured design review, running the other skills as a diagnostic funnel from complexity triage to a full red-flags sweep. Use when the user asks for a comprehensive or prioritized design assessment of a file, module, or PR. Not for an open-ended "anything off here?" or "take a look at this" prompt that names no review goal (use red-flags), a plain diff review before merge or analyzing how code changed over time (use code-evolution), or applying one specific lens (use that skill directly).

    Annotations the server declares

    • readOnlyHint: true
  • diagnoseRoutes a vague symptom or complaint to the most relevant Clairvoyance skill via a decision tree.No 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.
    Description, as the server wrote it
    Routes a vague symptom or complaint to the most relevant Clairvoyance skill via a decision tree. Use when someone describes a problem but doesn't know which skill to reach for. Not for a comprehensive review (use design-review) or a checklist scan (use red-flags).

    Annotations the server declares

    • readOnlyHint: true
  • error-designReviews error handling and exception design, applying the "define errors out of existence" principle.No 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.
    Description, as the server wrote it
    Reviews error handling and exception design, applying the "define errors out of existence" principle. Use when reviewing error handling, when a module throws too many exceptions, or when callers must handle errors they shouldn't need to know about. Not for general caller-burden complexity (use pull-complexity-down); this skill is specifically for exception and error-condition strategy.

    Annotations the server declares

    • readOnlyHint: true
  • general-vs-specialEvaluates whether interfaces are appropriately general-purpose.1 finding

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "general-vs-special" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Evaluates whether interfaces are appropriately general-purpose. Use when checking interface generality, when if-branches or parameters serve only one caller, or when getters/setters expose internal representation. Not for information leakage across boundaries (use information-hiding) or auditing configuration parameters (use pull-complexity-down).

    Annotations the server declares

    • readOnlyHint: true
  • information-hidingChecks for information leakage across module boundaries, including temporal decomposition and false encapsulation.No 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.
    Description, as the server wrote it
    Checks for information leakage across module boundaries, including temporal decomposition and false encapsulation. Use when modules change together, implementation details leak across boundaries, or structure follows execution order rather than knowledge ownership. Not for merge/split decisions (use module-boundaries) or interfaces over-specialized for one caller (use general-vs-special).

    Annotations the server declares

    • readOnlyHint: true
  • module-boundariesEvaluates where module boundaries are drawn and whether modules should be merged or split.1 finding

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "module-boundaries" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Evaluates where module boundaries are drawn and whether modules should be merged or split. Use when deciding whether to combine or separate two modules, when modules are tightly coupled, or when a change to one forces changes to another. Not for depth within a single module (use deep-modules) or abstraction-layer quality (use abstraction-quality).

    Annotations the server declares

    • readOnlyHint: true
  • naming-obviousnessReviews naming quality and code obviousness via the isolation test, scope-length principle, and consistency audit.No 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.
    Description, as the server wrote it
    Reviews naming quality and code obviousness via the isolation test, scope-length principle, and consistency audit. Use when names feel vague, something is hard to name (a design signal, not a vocabulary problem), or behavior isn't obvious on first read. Not for comment quality or documentation (use comments-docs).

    Annotations the server declares

    • readOnlyHint: true
  • pull-complexity-downChecks whether complexity is pushed to callers or absorbed by implementations — the direction complexity flows.No 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.
    Description, as the server wrote it
    Checks whether complexity is pushed to callers or absorbed by implementations — the direction complexity flows. Use when callers must do significant setup, handle errors the module could resolve, or configure things they don't understand. Not for module depth (use deep-modules), knowledge leakage (use information-hiding), or exception strategy once an error must surface (use error-design).

    Annotations the server declares

    • readOnlyHint: true
  • red-flagsScans code against 17 design smells (the book's 14 named Red Flags plus 3 process-stage signals) and produces a structured diagnostic report.No 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.
    Description, as the server wrote it
    Scans code against 17 design smells (the book's 14 named Red Flags plus 3 process-stage signals) and produces a structured diagnostic report. Use when the user asks for a red flags or design smell scan, asks to check code against a checklist, is evaluating unfamiliar code, or asks open-endedly whether anything is off in a named or pasted file, class, or function, or asks you to look it over. Not for a specific bug, error, or failing test the user has already identified. Not for a plain diff or PR review before merge, or whether a PR maintains design trajectory (use code-evolution for both), or diagnosing why code feels complex (use complexity-recognition).

    Annotations the server declares

    • readOnlyHint: true
  • strategic-mindsetAssesses whether code reflects strategic or tactical thinking, including the 10-20% investment rule and tactical-tornado patterns.No 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.
    Description, as the server wrote it
    Assesses whether code reflects strategic or tactical thinking, including the 10-20% investment rule and tactical-tornado patterns. Use when evaluating design investment, when code was written under time pressure, or when working code consistently degrades the system. Not for judging whether a specific diff looks designed-in or bolted-on (use code-evolution).

    Annotations the server declares

    • readOnlyHint: true
Only reads 1Show 1 read-only tool
  • fetch-referenceFetch a supporting file from a Clairvoyance skill's references/ folder, when the skill's instructions point to one.Reads private dataNo findings

    Why it is in this group

    • The name "fetch-reference" says "fetch": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "file": it reads files.
    • private-dataThe input names a file (input.file), and the tool reads: it reads files.
    Description, as the server wrote it
    Fetch a supporting file from a Clairvoyance skill's references/ folder, when the skill's instructions point to one. Available: information-hiding (back-door-leakage.md); pull-complexity-down (configuration-parameter-audit.md); comments-docs (comments-first-workflow.md); design-it-twice (pre-mortem-fallback.md); red-flags (flag-interaction-map.md); design-review (workflow-builder.md).

    Annotations the server declares

    • readOnlyHint: 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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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, 18:54 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
16
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 16 tools that change things (16 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://clairvoyance.fyi/mcp: tools/list returned 17 tools to an anonymous client, including deep-modules (write), module-boundaries (write), information-hiding (write), pull-complexity-down (write), general-vs-special (write) and 11 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

6 warn
  • The server marks "module-boundaries" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

    What this check looks for
  • The server marks "general-vs-special" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

    What this check looks for
  • The server marks "abstraction-quality" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

    What this check looks for
  • The server marks "comments-docs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The name "comments-docs" says "comment": a word for a change.

    What this check looks for
  • The server marks "design-it-twice" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The description's first verb is "generate": a word for a change.

    What this check looks for
  • The server marks "code-evolution" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The description's first verb is "evaluate": a word for a change.

    What this check looks for

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.3.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http clairvoyance https://clairvoyance.fyi/mcp
claude mcp add --transport http clairvoyance https://clairvoyance.fyi/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__clairvoyance__fetch-reference"
    ],
    "ask": [
      "mcp__clairvoyance__deep-modules",
      "mcp__clairvoyance__module-boundaries",
      "mcp__clairvoyance__information-hiding",
      "mcp__clairvoyance__pull-complexity-down",
      "mcp__clairvoyance__general-vs-special",
      "mcp__clairvoyance__error-design",
      "mcp__clairvoyance__abstraction-quality",
      "mcp__clairvoyance__naming-obviousness",
      "mcp__clairvoyance__comments-docs",
      "mcp__clairvoyance__strategic-mindset",
      "mcp__clairvoyance__design-it-twice",
      "mcp__clairvoyance__code-evolution",
      "mcp__clairvoyance__complexity-recognition",
      "mcp__clairvoyance__red-flags",
      "mcp__clairvoyance__design-review",
      "mcp__clairvoyance__diagnose"
    ],
    "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 clairvoyance. Review it before you use it.

Capability tags behind 1 rule
  • mcp__clairvoyance__fetch-reference private-data

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/fyi.clairvoyance/mcp/verify?hash=b8ce46c742a3e907e5884c624b9dab02b2a2e392bdca3e1fed82f9dd4c7b54c2" | jq -e '.changed == false'

Pinned hash b8ce46c742a3, from Nov 11, 2026, 13:18 UTC.

Watch

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

https://radar.anlyon.com/servers/fyi.clairvoyance/mcp/changes.xml

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

Badge

Anlyon Radar badge for fyi.clairvoyance/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/fyi.clairvoyance/mcp.svg)](https://radar.anlyon.com/servers/fyi.clairvoyance/mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:12 UTC.

Clairvoyance MCP server: questions and answers

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

Is the Clairvoyance MCP server safe?

No scan can promise that. What its definitions show: 17 tools, 16 of which can change, send or delete something, and 6 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 Clairvoyance MCP server delete data?

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

Can the Clairvoyance 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 Clairvoyance MCP server have?

17 tools: 16 write, 1 read. deep-modules, module-boundaries, information-hiding, pull-complexity-down, general-vs-special, error-design, abstraction-quality, naming-obviousness and 9 more.

Does the Clairvoyance MCP server need sign-in or OAuth?

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

Does the Clairvoyance MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Clairvoyance MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.