Skip to main content
Glama
MarwanDevSpace

mcp-flutter-apk-injector

by MarwanDevSpace
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Search reverse-engineering memory graph

query_memory_graph
Read-onlyIdempotent

Search and inspect historical patch logs, register allocations, decompilation metadata, and security findings in the memory graph to locate specific components by keyword.

Instructions

Search and inspect historical patch logs, register allocations, decompilation metadata, native libraries, and security findings in the active memory graph. This operation is read-only, non-mutating, and idempotent; performs fuzzy substring matching on query and returns ranked results by match score. Use query_memory_graph to locate specific patch records, hook locations, or components by keyword; use get_agent_context instead for a full session snapshot, and update_agent_memory to store new observations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesCase-insensitive search string matching package names, launcher activities, patch history details, security markers, native libraries, or agent notes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesOriginal query search string.
resultsYesRanked list of matching memory graph elements.
matchesCountYesTotal number of matching memory graph nodes found.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.4
    • changedInput schema / properties / query / description
      Previous value: -"Search term for patch history, packages, activities, or notes"New value: +"Case-insensitive search string matching package names, launcher activities, patch history details, security markers, native libraries, or agent notes"
    • addedInput schema / properties / query / minLength
      Added value: +1
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "matchesCount": {
+      "description": "Total number of matching memory graph nodes found.",
+      "minimum": 0,
+      "type": "integer"
+    },
+    "query": {
+      "description": "Original query search string.",
+      "type": "string"
+    },
+    "results": {
+      "description": "Ranked list of matching memory graph elements.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "category": {
+            "description": "Memory graph node category (e.g. Package Name, Patch, Agent Note).",
+            "type": "string"
+          },
+          "matchScore": {
+            "description": "Relevance match score (higher indicates more specific match).",
+            "type": "number"
+          },
+          "value": {
+            "description": "Matched node string value or patch detail.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "category",
+          "value",
+          "matchScore"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "query",
+    "matchesCount",
+    "results"
+  ],
+  "type": "object"
+}
  2. Addedv0.1.3

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral specifics beyond that: fuzzy substring matching on the query and ranked results by match score. It also reiterates non-mutating and idempotent, which is consistent. The extra details about matching behavior add value beyond the annotations.

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?

Three sentences with no redundancy. The purpose is front-loaded, usage guidance follows, and no filler. Highly efficient and well-structured.

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?

The description covers purpose, usage alternatives, behavioral traits, and the single parameter is well-documented in the schema. Output schema exists, so return format is not needed. Complete for a read-only search tool.

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

Parameters3/5

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

Schema coverage is 100% and the single parameter 'query' has a descriptive schema entry listing what it matches (package names, launcher activities, etc.). The description adds 'fuzzy substring matching' which slightly extends semantics, but it's a minor addition. Baseline of 3 is appropriate given the schema already carries the meaning.

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?

States a specific verb ('Search and inspect') and resource ('memory graph'), lists the data types it covers (patch logs, register allocations, etc.), and explicitly names sibling tools (get_agent_context, update_agent_memory) to distinguish itself. The title reinforces the search function. Clear differentiation from siblings.

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?

Explicitly instructs when to use this tool (locate specific patch records, hook locations, or components by keyword) and provides two alternatives: get_agent_context for a full session snapshot and update_agent_memory to store new observations. This is a model of usage guidance, leaving no ambiguity.

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

Deploy Server

Other Tools