optiqra-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPTIQRA_BASE_URL | No | Base URL of the OptiQra instance to call. Defaults to https://optiqra.vercel.app. | https://optiqra.vercel.app |
| OPTIQRA_TIMEOUT_MS | No | Request timeout in ms. Defaults to 120000 (full-site crawls can be slow). | 120000 |
| OPTIQRA_PROVIDER_API_KEY | No | A default AI-provider API key used by optiqra_ai_fix/optiqra_ai_insights/optiqra_ai_test if the model doesn't pass one. Recommended over letting the model handle the key in plaintext. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| optiqra_analyzeA | Crawls a website and runs OptiQra's full audit: SEO, GEO (generative engine optimization), AEO (answer engine optimization), performance, accessibility, security headers, structured data, links, images, and duplicate-content detection. Returns a report with per-category scores and issue details. This can take a while for larger sites since it crawls the whole site. |
| optiqra_ai_fixA | Given a single issue from an OptiQra report (as produced by optiqra_analyze), asks an AI provider to generate a suggested fix. Requires an API key for the chosen provider — OptiQra forwards it directly to that provider and never stores it server-side. |
| optiqra_ai_insightsA | Given a full OptiQra report (as produced by optiqra_analyze), asks an AI provider to generate a strategic, site-wide summary reasoning across all audit categories and pages. Requires an API key for the chosen provider — OptiQra forwards it directly to that provider and never stores it server-side. |
| optiqra_ai_testA | Verifies that a given AI provider + API key + model combination is reachable and working, before using optiqra_ai_fix or optiqra_ai_insights. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a distinct purpose: optiqra_analyze performs the site audit, while optiqra_ai_test validates AI connectivity, optiqra_ai_fix addresses individual issues, and optiqra_ai_insights provides site-wide strategy. No two tools overlap meaningfully; the input scope (single issue vs full report) clearly separates the AI generation tools.
All tools share the 'optiqra_' prefix and snake_case convention. The naming pattern is mostly consistent: 'optiqra_ai_*' for AI-related tools and 'optiqra_analyze' for the audit. The slight deviation is that 'optiqra_analyze' lacks the 'ai_' component, but this is logical since the audit is independent of AI providers.
With exactly 4 tools, the server is tightly scoped for its purpose: one comprehensive audit tool and three supporting AI utilities. Each tool fills a necessary role in the workflow, and the count is neither inflated nor insufficient.
The tool set covers the full lifecycle of an audit automation: optiqra_analyze generates the report, optiqra_ai_test ensures AI availability, and then optiqra_ai_fix/insights provide actionable output. There are no obvious missing functions—the report includes detailed issues and scores, and the AI tools address both granular and strategic needs.