rankparse-mcp

get_keyword_rank_history

Read-onlyIdempotent

Get the stored day-by-day ranking history for one keyword on one search engine over a date range. Reads RankParse snapshots synced on a schedule; it is not a live SERP check. History is inherently single-engine, so engine is required (use get_keyword_rankings first to compare across engines). Days with no synced data are simply absent from rows rather than filled with a zero or placeholder value -- do not treat a missing date as "not ranking". Bing and Yandex are opt-in and lower-frequency than Google; their responses may report availability as provider_limited, meaning that provider did not return enough data for that day rather than the keyword ranking nowhere.

Input Schema

TableJSON Schema

Name	Required	Description
`engine`	Yes	Search engine to get history for (required -- history is always single-engine)
`site_id`	Yes	Logical RankParse website ID, from list_rank_tracking_sites
`end_date`	Yes	End of the range, inclusive, as YYYY-MM-DD
`dimension`	No	Breakdown of the daily rows. Default "total" is one row per day; "device" is one row per day per device (desktop/mobile/tablet) with a device field on each row. Device rows exist only where the provider synced them (always for Google; Yandex only when its device breakdown is enabled), so an empty device history for a keyword with total history means "not synced per-device", not "no traffic".
`keyword_id`	Yes	Tracked keyword ID, from list_tracked_keywords
`start_date`	Yes	Start of the range, inclusive, as YYYY-MM-DD

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 16, 2026

addedInput schema / properties / dimension

Added value: +{
+  "description": "Breakdown of the daily rows. Default \"total\" is one row per day; \"device\" is one row per day per device (desktop/mobile/tablet) with a device field on each row. Device rows exist only where the provider synced them (always for Google; Yandex only when its device breakdown is enabled), so an empty device history for a keyword with total history means \"not synced per-device\", not \"no traffic\".",
+  "enum": [
+    "total",
+    "device"
+  ],
+  "type": "string"
+}

AddedSep 5, 2026

TDQS

A5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, but the description adds crucial behavioral context beyond these: it reads stored snapshots (not live), missing days are absent rather than zero, and provider_limited indicates insufficient provider data. This prevents misinterpretation and exceeds what annotations alone convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is thorough but every sentence earns its place. It front-loads the primary purpose, then logically addresses caveats: non-live nature, single-engine requirement, missing data semantics, and provider_limited status. No redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with 6 parameters (5 required), the description covers all critical nuances: date handling, missing data interpretation, engine-specific behavior, and output row structure (mentions rows and device field). Although no output schema exists, the description gives enough to understand what will be returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions, so the baseline is 3. However, the description adds meaningful semantics: for 'engine' it reiterates the requirement and single-engine nature; for 'dimension' it explains the difference between 'total' and 'device' rows and clarifies that missing device rows mean 'not synced per-device' rather than no traffic. This goes well beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'get' and the specific resource: 'stored day-by-day ranking history for one keyword on one search engine over a date range.' It distinguishes itself from siblings by explicitly noting it is not a live SERP check and that engine is required because history is single-engine, referencing get_keyword_rankings for cross-engine comparisons.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance: 'History is inherently single-engine, so engine is required (use get_keyword_rankings first to compare across engines).' It also warns about Bing/Yandex being opt-in and lower-frequency, and explains the meaning of provider_limited, which helps the agent decide when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All rankparse-mcp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?