Search Evidence
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEARCH_EVIDENCE_PROFILE | Yes | Absolute path to the private profile TOML file used to launch the stdio MCP server. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_statusC | Show local availability and optionally check account/property access. |
| search_collectC | Collect read-only Google/Bing reports into private local storage. |
| search_trafficC | Read one explicit snapshot; missing rows are unknown. |
| search_compareC | Compare compatible equal-length Google periods. |
| search_protect_urlsC | Show raw URLs protected by any historical positive clicks. |
| search_prioritizeC | Prioritize audit findings while preserving protected URLs. |
| search_inspect_urlsC | Read indexed Google/Bing records and persist observations. |
| search_audit_contentC | Audit the configured content root; never edit its files. |
| search_verify_liveC | Compare a registered reviewed build with public live HTML. |
| search_render_reportC | Write JSON, safe CSV and escaped HTML under private state. |
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 10 tools
Each tool targets a fairly distinct stage of an SEO evidence pipeline (collect, inspect, audit, compare, protect, prioritize, verify, report). The main soft overlap is among read-oriented tools like inspect_urls, traffic, and collect, but the descriptions differentiate indexed records vs a single snapshot vs bulk report collection.
All tools share a consistent snake_case 'search_' namespace prefix, making the set easy to scan. A few second segments are bare nouns (status, traffic, collect) rather than strict verb_noun, a minor deviation.
Ten tools is a well-scoped size for a read-only SEO evidence workflow, with each tool covering a distinct step. Nothing feels redundant or padded.
The surface covers collection, auditing, comparison, protection, prioritization, live verification, and reporting, which is broad for the domain. Minor gaps exist around configuration or account setup beyond the access check in search_status.