mcp-code-intel

A set of code-analysis tools for Android projects written in Kotlin or Java. It helps an agent inspect symbols, references, project structure, dependencies, and common Android frameworks.

In plain words
What is it for?
Use it to find classes and methods, see who uses or calls them, inspect dependency impact, query project details, and analyze Android code.
Why use it?
It gives the agent information about how code is connected, making analysis and refactoring work more grounded in the project structure.

Skill for Claude CodeCodexCursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/starsmilky/mcpcodeintelligence/mcp-code-intelligence
Any agent
npx skills add StarsMilky/MCPCodeIntelligence --skill mcp-code-intelligence
Clone the repo
git clone --depth 1 https://github.com/StarsMilky/MCPCodeIntelligence

Made for: Claude Code, Codex, Cursor.

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00124 $0.03332
Opus 5 $0.00062 $0.01666
Sonnet 5 $0.00025 $0.00666
Haiku 4.5 $0.00012 $0.00333

Measured yesterday against content hash 67caa1b31696, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-code-intel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/MCP Code Intelligence/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Code Intelligence

13 IDE-level tools for AI agents. Always prefer these over CLI equivalents.

Every tool response includes a nextAction hint suggesting the best follow-up call — use it to chain tools.

Quick Reference

Task Tool Call
Find a symbol by name find_symbol(name="UserRepository", kind="CLASS")
Find a symbol by FQN find_symbol(name="com.example.UserRepository")
What type is this? resolve_symbol(file, line, column)
Who uses this symbol? (by name) find_references(qualified_name="com.example.Foo", mode="USAGES")
Who uses this symbol? (by pos) find_references(file, line, col, mode="USAGES")
Who calls this method? find_references(qualified_name="com.Foo.bar", mode="CALLERS", depth=3)
What does this method call? find_references(file, line, col, mode="CALLEES")
Class hierarchy find_references(qualified_name="com.Foo", mode="TYPE_HIERARCHY")
Symbols at cursor get_scope(file, line, col, filter="ALL")
Project overview query_project(mode="OVERVIEW")
Dependency impact query_project(mode="DEPENDENCY", target_class="com.Foo")
Framework details query_framework(framework="ROOM", detail_target="UserEntity")
Null safety check analyze_data_flow(file, line, col, mode="NULLABILITY")
Value tracing analyze_data_flow(file, line, col, mode="BACKWARD")
Quality hotspots analyze_quality(mode="COMPLEXITY", top_n=10)
Architecture rules check_rules(rules=[...])
Pattern search structural_search(pattern="@Composable fun $X$")
Rename safely refactor(operation="RENAME", file, line, col, new_name="New")
Create checkpoint checkpoint(operation="CREATE", label="before-fix")
Decompile class sandbox(operation="DECOMPILE", qualified_class_name="...")

Critical Rules

  1. NEVER use grep/rg for code references → find_references(mode="USAGES")
  2. NEVER use grep/rg to locate a symbol → find_symbol(name="SymbolName")
  3. NEVER guess types → resolve_symbol(file, line, column)
  4. NEVER use sed/text-replace for renaming → refactor(operation="RENAME")
  5. NEVER start multi-file changes without → checkpoint(operation="CREATE")
  6. ALWAYS start with query_project(mode="OVERVIEW") on a new project
  7. ALWAYS use find_symbol(name=...) to locate symbols instead of grep
  8. All enum values are UPPERCASE: "USAGES", "RENAME", "OVERVIEW", not "usages"
  9. find_references accepts two entry modes: file+line+column (position) OR qualified_name (name-based). resolve_symbol is position-only — use find_symbol for name-based lookup.

Read the full file on GitHub · 285 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 285 lines · 124 tokens per session scan A 67caa1b31696

Subscribe to this mod's changes

mcp-code-intel is a skill published in the GitHub repository StarsMilky/MCPCodeIntelligence (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 124 tokens to every session and 3,332 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

orca-emulator-android

Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…

stablyai/orca · 104 tokens

speckit-analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

unoplatform/uno · 32 tokens

add-sample

Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.

unoplatform/uno · 21 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens