AEO Scanner
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AEO_API_KEY | No | Optional API key required for paid tools (audit_site, compare_sites, fix_site). Get your key at https://scan.convrgent.ai |
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 |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_siteB | Quick AI visibility scan. Returns three scores: AEO Score (0-100, AI search findability), GEO Score (0-100, AI citation readiness), and Agent Readiness Score (0-100, AI agent interaction). Also returns AI Identity Card with mention readiness (0-100, predicts how likely AI will mention the brand), detected competitors, business profile (commerce/saas/media/general), and top issues. 58+ checks across 12 categories. Free — no API key needed. |
| audit_siteA | Full AI visibility audit across 58+ checks in 12 categories: AEO (structured data, meta & technical, AI accessibility, content quality), GEO (brand narrative, citation readiness with 3 research-backed checks, authority signals, entity definition), and Agent Readiness (machine identity, API discoverability, structured actions, programmatic access). Returns AI Identity Card with mention readiness and detected competitors. Requires API key (set AEO_API_KEY env var). $1.00 per call. |
| compare_sitesA | Competitive gap analysis — scans two sites concurrently, shows side-by-side scores, category-by-category winners, competitive gaps (checks where competitor scored 20+ higher), and generated overtake fix code with projected scores after closing gaps. Use when the user wants to benchmark against a competitor or when scan_site detects competitors in the AI Identity Card. Requires API key (set AEO_API_KEY env var). $3.00 per call. |
| fix_siteA | Generate complete fix code for all AI visibility issues across AEO, GEO, and Agent Readiness. Returns working code that coding agents can apply directly. Includes two-tier score projections: quick wins (critical + high fixes only) and full implementation ceiling (all fixes). Content recommendations include research citations. Set format to 'claude_code' for Claude Code optimized output. Requires API key (set AEO_API_KEY env var). $5.00 per call. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| optimize_site | Full scan → audit → compare → fix → verify workflow for optimizing a site's AI visibility. Uses detected business profile to prioritize which scores matter most. Includes competitive analysis when competitors are detected. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| scoring_methodology | How AEO, GEO, and Agent Readiness scores are calculated across 58+ checks in 12 categories. Includes mention readiness, business profiles, and research sources. |
TDQS
Scored across 4 tools
The main ambiguity is between scan_site and audit_site, which both claim 58+ checks across 12 categories and return the same AI Identity Card components; the free/paid and quick/full distinctions help but the boundary is fuzzy. compare_sites is clearly a two-site benchmark and fix_site is clearly code generation, so the rest are distinct.
All tools follow a verb_noun pattern (scan_site, audit_site, fix_site) with one minor deviation: compare_sites uses a plural noun while the others are singular. The verb choices are clear and consistent in style.
Four tools is well-scoped for a scanner/remediation server: quick scan, full audit, competitive comparison, and fix generation. Each tool earns a clear place in the workflow with a distinct price point.
The surface forms a complete lifecycle: free scan for instant signal, paid audit for depth, compare for benchmarking, and fix_site for remediation. Verification after applying fixes is possible by calling scan_site again, so the loop has no dead ends.