# io.github.pathmodeio/mcp-server (npm · @pathmode/mcp-server)

Build intent specs via Socratic AI conversation. Connect to your Intent Layer for context.

- Trust score: 67/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@pathmode/mcp-server`: 67/100 (this document), [markdown](https://verifymcp.io/servers/pathmodeio-mcp-server/pathmode-mcp-server.md), [page](https://verifymcp.io/servers/pathmodeio-mcp-server/pathmode-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@pathmode/mcp-server`
- Version: `1.6.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (105 of 109), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (105 of 109), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 42 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 68/100
  - 63% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1759 tokens (~76/item across 23 items; 20 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add pathmodeio-mcp-server -- npx -y @pathmode/mcp-server
```

### Codex

```bash
codex mcp add pathmodeio-mcp-server -- npx -y @pathmode/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pathmodeio-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pathmode/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pathmodeio-mcp-server --command npx --arg -y --arg @pathmode/mcp-server
```

### Hermes

```yaml
mcp_servers:
  pathmodeio-mcp-server:
    command: "npx"
    args: ["-y", "@pathmode/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "pathmodeio-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@pathmode/mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 67, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 64, +41)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 63 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-07-31 (score 23, +17)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 6, −43)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 63 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-27 (score 49)

First indexed and scored.

## MCP tools (20)

### `get_current_intent` (~67 tokens)

Get Current Intent

Get the currently active intent, preferring approved intents with real objective/outcome content over empty stubs. Returns the full IntentSpec with objective, outcomes, constraints, and edge cases.

Input parameters:

- `status` (string): Filter by status: draft, validated, approved, shipped, verified

### `list_intents` (~51 tokens)

List Intents

List all intents in the workspace. Returns an array of IntentSpecs with their status, objectives, and metadata.

Input parameters:

- `status` (string): Filter by status: draft, validated, approved, shipped, verified

### `get_intent` (~44 tokens)

Get Intent

Get a single intent by ID with full details including objective, outcomes, constraints, edge cases, and relations.

Input parameters:

- `intentId` (string, required): The intent ID to fetch

### `get_intent_relations` (~46 tokens)

Get Intent Relations

Get the dependency graph for a specific intent. Shows what it depends on, enables, or blocks.

Input parameters:

- `intentId` (string, required): The intent ID to get relations for

### `search_intents` (~57 tokens)

Search Intents

Search intents by keyword. Searches across user goals, objectives, outcomes, and constraints.

Input parameters:

- `query` (string, required): Search keyword or phrase
- `status` (string): Filter by status: draft, validated, approved, shipped, verified

### `analyze_intent_graph` (~65 tokens)

Analyze Intent Graph

Analyze the intent dependency graph for risks and strategic insights. Returns critical path, cycles, bottlenecks, orphans, status mismatches, and stalled intents.

Input parameters:

- `analysis` (string): Type of analysis: full (default), critical-path, risks, or status distribution

### `export_context` (~193 tokens)

Export Context

Export workspace context as a formatted file. Use "claude-md" for CLAUDE.md (full workspace context), "cursorrules" for Cursor AI rules, "intent-md" for a single intent specification file, or "outcome-rubric" for a Claude Managed Agents Outcomes rubric (writer description + evidence-forcing grader rubric) derived from the resolved intent, its implementation context, and the workspace constitution. For cursorrules/intent-md/outcome-rubric, product context is always derived from the resolved intent. For claude-md, pass productId to select a specific product, otherwise the first active product is used.

Input parameters:

- `format` (string, required): Export format
- `intentId` (string): Intent ID (optional, for cursorrules and intent-md)
- `productId` (string): Product ID (optional, only used for claude-md format to select a specific product)

### `get_agent_prompt` (~72 tokens)

Get Agent Prompt

Get a formatted execution prompt for a specific intent. This is the full structured prompt including objective, outcomes, constraints, edge cases, and verification steps.

Input parameters:

- `intentId` (string, required): The intent ID to generate a prompt for
- `mode` (string): draft = critique the spec, execute = implement it

### `get_workspace` (~31 tokens)

Get Workspace

Get workspace details including strategy (vision, non-negotiables, architecture principles), active products, and constitution rules.

### `get_constitution` (~26 tokens)

Get Constitution

Get the workspace constitution rules. These are mandatory constraints that all implementations must respect.

### `update_intent_status` (~82 tokens)

Update Intent Status

Update the status of an intent. Use this to mark an intent as shipped after implementation, or verified after testing. For shipped/verified transitions, the response includes a verification checklist of outcomes, constitution rules, and health metrics that should be confirmed.

Input parameters:

- `intentId` (string, required): The intent ID to update
- `status` (string, required): The new status

### `log_implementation_note` (~61 tokens)

Log Implementation Note

Record a technical decision or implementation note for an intent. Use this to document why you chose a specific approach.

Input parameters:

- `intentId` (string, required): The intent ID to attach the note to
- `note` (string, required): The implementation note or technical decision

### `create_intent` (~190 tokens)

Create Intent

Create a new intent spec in the workspace. Requires at minimum a title, objective, and productId. Returns the created intent with its ID. Use list_intents first to see existing intents and avoid duplicates.

Input parameters:

- `constraints` (array): Hard limits the implementation must respect
- `edgeCases` (array): Failure modes and boundary conditions
- `healthMetrics` (array): What to monitor after shipping
- `objective` (string, required): Why this matters — the problem and who has it
- `outcomes` (array): Observable, testable state changes
- `problemSeverity` (string): How severe the problem is
- `productId` (string, required): Product (Space) ID this intent belongs to. Use get_workspace to find product IDs.
- `title` (string, required): Short name for the intent (e.g., "Improve onboarding flow")
- `verification` (object): How to confirm it works

### `update_intent` (~132 tokens)

Update Intent

Update an existing intent's content. Provide only the fields you want to change. Does NOT change intent status (use update_intent_status for that).

Input parameters:

- `constraints` (array): Replace all constraints
- `edgeCases` (array): Replace all edge cases
- `healthMetrics` (array): Replace all health metrics
- `intentId` (string, required): The intent ID to update
- `objective` (string): Updated objective
- `outcomes` (array): Replace all outcomes
- `problemSeverity` (string)
- `title` (string): New title
- `verification` (object): Replace verification plan

### `query_evidence` (~128 tokens)

Query Evidence

Search evidence items (friction points, user quotes, observations, metrics, feature requests) by product, type, severity, or text. Returns matching evidence with IDs that can be linked to intents.

Input parameters:

- `limit` (number): Max results (default 50, max 200)
- `productId` (string): Filter by product (Space) ID
- `search` (string): Text search across evidence content
- `severity` (string): Filter by severity
- `tags` (string): Comma-separated tags to filter by
- `type` (string): Filter by evidence type

### `create_evidence` (~190 tokens)

Create Evidence

Create a new evidence item (e.g., a discovered bug, user feedback quote, behavioral observation, or feature request). Evidence can later be linked to intents to support prioritization.

Input parameters:

- `content` (string, required): The evidence content — a finding, quote, or observation
- `productId` (string, required): Product (Space) ID this evidence belongs to
- `sentiment` (string): Emotional sentiment
- `severity` (string): Severity level (required for friction type)
- `source` (string): Where this evidence came from (e.g., "User interview", "Bug report", "Support ticket")
- `sourceUrl` (string): URL to the original source
- `stage` (string): Workflow stage (e.g., "Discovery", "Checkout")
- `tags` (array): Category tags (e.g., ["Onboarding", "Performance"])
- `type` (string, required): Type of evidence

### `link_evidence` (~76 tokens)

Link Evidence to Intent

Link or unlink evidence items to/from an intent. Linking evidence to intents establishes traceability between user problems and planned solutions.

Input parameters:

- `intentId` (string, required): The intent ID to link evidence to
- `link` (array): Evidence IDs to link to this intent
- `unlink` (array): Evidence IDs to unlink from this intent

### `verify_implementation` (~99 tokens)

Verify Implementation

AI-grade your implementation against the intent spec. Checks each outcome, constraint, constitution rule, and edge case. Returns pass/fail per item with reasoning and an overall score. Also logs the result as an implementation note.

Input parameters:

- `codeChanges` (string): Summary of code changes (file list, key modifications)
- `intentId` (string, required): The intent ID to verify against
- `summary` (string, required): Description of what was implemented and how

### `intent_save` (~52 tokens)

Save an intent spec to intent.md in the project root. Called after building a spec through conversation.

Input parameters:

- `path` (string): File path relative to cwd. Defaults to intent.md
- `spec` (object, required)

### `intent_export` (~77 tokens)

Export an intent spec as .cursorrules, a CLAUDE.md section, or a Claude Managed Agents Outcomes rubric for AI agent consumption.

Input parameters:

- `format` (string, required): Export format
- `path` (string): Output file path. Defaults to .cursorrules or CLAUDE.md
- `spec` (object, required)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pathmodeio-mcp-server/pathmode-mcp-server#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 64
- 2026-08-01: 23
- 2026-07-31: 23
- 2026-07-30: 6
- 2026-07-28: 49
- 2026-07-27: 49

## Links

- npm package: https://www.npmjs.com/package/@pathmode/mcp-server
- Socket report: https://socket.dev/npm/package/@pathmode/mcp-server
- Repository: https://github.com/pathmodeio/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/pathmodeio-mcp-server/pathmode-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/pathmodeio-mcp-server/pathmode-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/pathmodeio-mcp-server/pathmode-mcp-server