RuneScape Wiki MCP: GE Analytics & References

Lookup Item

lookup_item

Read-onlyIdempotent

Resolve tradeable RS3 names to GE IDs. Use search_wiki for quests, NPCs or guides; non-GE items cannot match here.

query="Abyssal whip" tries an exact match; "abyssal" discovers alternatives. An exact match ends the search regardless of limit.
limit also bounds Wiki candidates checked against Weirdgloop. Non-GE candidates are discarded, so results can be fewer; increasing limit widens that screening. Values outside 1–10 error before fetching rather than being clamped.
Pass a chosen ID to get_item_details for current records, get_price_series for history, or estimate_flip for profit math. No matches is a tool error; optional price/volume fields may be absent and samples lag activity.
Reads are uncached and need no credentials. HTTP defaults to 60 requests/IP/minute; wait for Retry-After after 429.

Input Schema

Name	Required	Description	Default
`limit`	No	Max matches to return (default 5)
`query`	Yes	Item name or partial name to search for

Output Schema

Name	Required	Description	Default
`matches`	Yes	Matching Grand Exchange items, best match first

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "matches": {
+      "description": "Matching Grand Exchange items, best match first",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "error": {
+            "description": "Why this row could not be resolved",
+            "type": "string"
+          },
+          "id": {
+            "description": "Grand Exchange item ID",
+            "type": "integer"
+          },
+          "name": {
+            "description": "Item name",
+            "type": "string"
+          },
+          "price": {
+            "description": "Latest price in coins, when known",
+            "type": "number"
+          },
+          "timestamp": {
+            "description": "ISO timestamp of the price sample",
+            "type": "string"
+          },
+          "volume": {
+            "description": "Latest trade volume, when known",
+            "type": "number"
+          },
+          "wikiUrl": {
+            "description": "RuneScape Wiki page URL",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "matches"
+  ],
+  "type": "object"
+}

First observedOct 16, 2026

TDQS

A5/5.0

Behavior5/5

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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), it discloses operational traits the schema cannot: reads are uncached and credential-free, HTTP quota is 60 requests/IP/minute with Retry-After backoff on 429, and out-of-range limits error before any fetch. It also warns that optional price/volume fields may be missing and that samples lag activity, so the agent won't misread an empty field as an error.

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?

One lead sentence plus four scannable bullets, ordered from search semantics to limit semantics to next steps to operational constraints. No sentence repeats the name, title, or schema text verbatim.

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?

An output schema exists, so return shape need not be spelled out, and the description still covers the edge cases that matter: no matches is a tool error, nullable price/volume fields, and data staleness. For a two-parameter read tool this leaves nothing an agent needs for correct invocation.

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%, so the baseline is 3, but the description adds real meaning: an exact query ends the search regardless of limit, a partial query discovers alternatives, and limit bounds how many Wiki candidates get screened against Weirdgloop, so low limits can yield fewer results. It also clarifies that out-of-range values error rather than being clamped, which the schema alone doesn't say.

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?

"Resolve tradeable RS3 names to GE IDs" states a specific verb and resource plus the constraint that only GE-tradeable items match. It immediately distinguishes itself from the sibling search_wiki, which handles quests, NPCs and guides.

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?

It names the alternative (search_wiki) and the condition that selects it, and rules out non-GE items entirely. It also routes downstream: pass the chosen ID to get_item_details, get_price_series, or estimate_flip, giving the agent an explicit place in the workflow.

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

All RuneScape Wiki MCP: GE Analytics & References 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.