Developer Tools
clairvoyance.fyi
Analyzes software module design principles such as depth, boundaries, information hiding, complexity flow, and generality.
ENDPOINT 1
https://clairvoyance.fyi/mcp
MCP server metadata
- Name
- fyi.clairvoyance/mcp
- Version
- 1.3.1
Clairvoyance: software design skills for AI coding agents, inspired by A Philosophy of Software Design. Each tool named after a skill returns that skill's instructions. Call it when its description matches what you're doing, then follow it. Skills that link files in a references/ folder say how to load them with fetch-reference. Skills: - deep-modules: Measures module depth: whether the interface is simple relative to the implementation behind it. - module-boundaries: Evaluates where module boundaries are drawn and whether modules should be merged or split. - information-hiding: Checks for information leakage across module boundaries, including temporal decomposition and false encapsulation. - pull-complexity-down: Checks whether complexity is pushed to callers or absorbed by implementations — the direction complexity flows. - general-vs-special: Evaluates whether interfaces are appropriately general-purpose. - error-design: Reviews error handling and exception design, applying the "define errors out of existence" principle. - abstraction-quality: Evaluates whether abstractions provide a genuinely different way of thinking or are structurally shallow. - naming-obviousness: Reviews naming quality and code obviousness via the isolation test, scope-length principle, and consistency audit. - comments-docs: Reviews comment quality and documentation practices: the four comment types, comments-first workflow, and comment rot. - strategic-mindset: Assesses whether code reflects strategic or tactical thinking, including the 10-20% investment rule and tactical-tornado patterns. - design-it-twice: Generates and compares at least two fundamentally different design alternatives on concrete criteria before committing. - code-evolution: Evaluates whether changes to existing code maintain or degrade design quality. - complexity-recognition: Diagnoses whether complexity exists and where it comes from, using the three-symptom, two-root-cause framework. - red-flags: Scans code against 17 design smells (the book's 14 named Red Flags plus 3 process-stage signals) and produces a structured diagnostic report. - design-review: Orchestrates a structured design review, running the other skills as a diagnostic funnel from complexity triage to a full red-flags sweep. - diagnose: Routes a vague symptom or complaint to the most relevant Clairvoyance skill via a decision tree.
Known tools 17
deep-modulesMeasures module depth: whether the interface is simple relative to the implementation behind it.
Inferred read-onlymodule-boundariesEvaluates where module boundaries are drawn and whether modules should be merged or split.
Inferred read-onlyinformation-hidingChecks for information leakage across module boundaries, including temporal decomposition and false encapsulation.
Inferred read-onlypull-complexity-downChecks whether complexity is pushed to callers or absorbed by implementations — the direction complexity flows.
Inferred read-onlyerror-designReviews error handling and exception design, applying the "define errors out of existence" principle.
Inferred read-onlyabstraction-qualityEvaluates whether abstractions provide a genuinely different way of thinking or are structurally shallow.
Inferred read-onlynaming-obviousnessReviews naming quality and code obviousness via the isolation test, scope-length principle, and consistency audit.
Inferred read-onlycomments-docsReviews comment quality and documentation practices: the four comment types, comments-first workflow, and comment rot.
Inferred read-onlystrategic-mindsetAssesses whether code reflects strategic or tactical thinking, including the 10-20% investment rule and tactical-tornado patterns.
Inferred read-onlydesign-it-twiceGenerates and compares at least two fundamentally different design alternatives on concrete criteria before committing.
Inferred read-onlycode-evolutionEvaluates whether changes to existing code maintain or degrade design quality.
Inferred read-onlycomplexity-recognitionDiagnoses whether complexity exists and where it comes from, using the three-symptom, two-root-cause framework.
Inferred read-onlyred-flagsScans code against 17 design smells (the book's 14 named Red Flags plus 3 process-stage signals) and produces a structured diagnostic report.
Inferred read-onlydesign-reviewOrchestrates a structured design review, running the other skills as a diagnostic funnel from complexity triage to a full red-flags sweep.
Inferred read-onlydiagnoseRoutes a vague symptom or complaint to the most relevant Clairvoyance skill via a decision tree.
Inferred read-onlyfetch-referenceFetch a supporting file from a Clairvoyance skill's references/ folder, when the skill's instructions point to one.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.fyi-clairvoyance-mcp]
url = "https://clairvoyance.fyi/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"fyi-clairvoyance-mcp": {
"type": "http",
"url": "https://clairvoyance.fyi/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: fyi-clairvoyance-mcp
Remote MCP URL: https://clairvoyance.fyi/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"fyi-clairvoyance-mcp": {
"url": "https://clairvoyance.fyi/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"fyi-clairvoyance-mcp": {
"type": "http",
"url": "https://clairvoyance.fyi/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "fyi-clairvoyance-mcp",
"transport": "streamable-http",
"url": "https://clairvoyance.fyi/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for clairvoyance.fyi was fetched 2026-10-19T03:12:12.837Z.
clairvoyance.fyi is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.