pathpilot-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_evidence_profileA | Analyze a GitHub repository OR a GitHub user profile URL and generate a learning roadmap. If a GitHub profile URL is provided, automatically inspect the user's public repositories to infer skills. |
| get_repository_snapshotA | Return a bounded, normalized repository snapshot (file tree, manifest, README, selected source content) without running the full analysis pipeline. |
| get_linkedin_profileB | Return user-authorized, normalized LinkedIn profile snapshot with declared skills, roles, education, certifications, and projects. |
| compare_profile_and_repository_skillsB | Identify self-reported LinkedIn skills that do / do not have matching GitHub evidence in the selected repository. |
| generate_evidence_cardsA | Return UI-ready evidence cards with highlights, summaries, sources, and next-step suggestions. Accepts an analysisId from a prior run, or an analysis object. |
| get_roadmap_signalA | Return verified/self-reported/partial/missing skill arrays plus the priority gap and a suggested next task from a prior analysisId or analysis object. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| review_unified_evidence | Summarize GitHub and LinkedIn evidence into a transparent, learner-facing overview. GitHub for verification; LinkedIn claims labeled self-reported. |
| recommend_next_project | Turn roadmap signal into one practical, concrete build task. Prioritize the prerequisite priority gap; include acceptance checks; avoid course lists. |
| explain_roadmap_change | Produce visible "Why this changed" text. Name GitHub evidence, LinkedIn context, and the exact sequence change relative to the baseline 4-week roadmap. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Full-Stack Developer Skill Matrix v1 | Target skills, evidence thresholds, and source/status definitions for the full-stack-developer pathway. |
| Technology Detection Rules v1 | GitHub detector rules, weights, and signal sources for evidence engine transparency. |
| Profile Normalization Rules v1 | LinkedIn field mappings, allowed profile signals, and skill canonicalization for consent-aware profile handling. |
| Full-Stack Developer 4-Week Baseline Roadmap v1 | Baseline 4-week sequence, checkpoints, and prerequisites used by the AI roadmap service to calculate a change. |
| Analysis Limits and Privacy Policies v1 | File/profile allowlist, budgets, excluded paths, and redaction rules used by analysis pipeline. |
| Evidence Card UI Schema v1 | UI data contract for frontend evidence cards. Keeps frontend cards stable across analysis changes. |
| Health Checks | Current health status of all registered health checks |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
TDQS
Scored across 6 tools
Each tool targets a distinct resource or stage of the analysis pipeline. The only potential confusion is between generate_evidence_cards and get_roadmap_signal, both of which consume an analysisId but produce different outputs; the descriptions make this clear.
All tool names follow a verb_noun pattern with underscores, which is consistent in style. The verbs vary (analyze, get, compare, generate) but are all action-oriented and the pattern is predictable.
Six tools is well within the ideal range for a specialized server. Each tool has a clear role in the workflow, and none are redundant or redundant-feeling.
The server covers the full lifecycle from raw profile/repo input to analysis and actionable outputs. Minor gaps exist, such as no explicit 'get full analysis' tool or list of prior analyses, but the core workflow is complete.