GEOMCP
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 |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_urlA | Fetch one public page as GEOMCP and audit server-delivered HTML. Returns evidence, scored checks, unknowns, and prioritized fixes. No JavaScript execution, vendor impersonation or citation prediction. |
| audit_htmlA | Audit HTML supplied by the user or a build pipeline. Makes no network requests. HTTP checks remain unknown. Base URL is used only to resolve links. |
| inspect_robotsA | Fetch origin /robots.txt and report declared policies for search, AI retrieval and training separately at the supplied page path. Does not prove live vendor access. |
| inspect_sitemapA | Fetch one public XML sitemap or sitemap index. Report malformed locations, duplicate URLs, date syntax and samples. Does not fetch child maps or check indexing. |
| compare_auditsA | Compare two GEOMCP 0.1.0 check reports. Unknowns and absent checks are coverage changes, never improvements. Pass prior audit objects directly; extra fields are ignored. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| improve-page | Audit a public page and produce an evidence-backed implementation plan. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| methodology |
TDQS
Scored across 5 tools
Each tool targets a distinct input and action: audit_url (network page), audit_html (supplied markup), inspect_robots, inspect_sitemap, and compare_audits. The only near-pair, audit_url vs audit_html, is clearly separated by input source and network behavior in the descriptions.
All names follow a consistent verb_noun snake_case pattern (audit_url, audit_html, inspect_robots, inspect_sitemap, compare_audits). Verbs vary (audit/inspect/compare) but each accurately reflects the operation without breaking the convention.
Five tools is a tight, well-scoped set that maps cleanly onto the audit workflow. It is on the lean side, with no batch or multi-page variants, but nothing is redundant.
The set covers page auditing from both live and supplied HTML plus robots.txt, sitemap, and report comparison. Gaps exist for batch/multi-URL audits and other GEO-relevant artifacts like llms.txt, but the core lifecycle is workable.