REA

[ Score explain ]

Why the Score is 7

Score v2 uses only observed signals. The displayed contribution is weight × value × 100. Missing factors are insufficient evidence.

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

10% weight × 0.33 value

3.3 points

An MCP surface is declared. No API is declared. Cost is unknown. 1 of 3 checklist fields are complete.

14% weight × 0.26 value

3.7 points

3 sources cover 1 evidence types. The latest dated evidence is 2026-10-10. Freshness is omitted unless observed as a signal.

insufficient evidence

insufficient evidence

insufficient evidence

Total7.00 → 7 after rounding

GitHub health: insufficient evidence

Agent use: insufficient evidence

Human notes: insufficient evidence

Composability: insufficient evidence

Benchmarks: insufficient evidence

[ Claims ]

Publisher-asserted record

Claims are what the publisher declares. Score uses observed signals, not these assertions, except for checklist fields derived from interfaces. MCP, API, cost, and license claims are marked verified, unverified, or contradicted from intake evidence.

Kind: resource
Interfaces: Interface
mcp
Model Context Protocol server

Interface
cli
Command-line interface
Functions: Function
Code
write or edit programs
Code Browse Code

Function
Test
prove behavior
Test Browse Test

Function
Connect
speak a protocol (MCP, API, CLI)
Connect Browse Connect

[ Capability slices ]

Compose the useful parts.

code

Code

README tagline: "One MCP for reverse engineering across binaries, applications, and runtime behavior." The agent calls REA through MCP to inspect a local target and trace relevant code; REA returns findings with their evidence, and the agent uses them to explain the behavior or write and test an implementation.

unknownCompose with this

test

Test

README tagline: "One MCP for reverse engineering across binaries, applications, and runtime behavior." The agent calls REA through MCP to inspect a local target and trace relevant code; REA returns findings with their evidence, and the agent uses them to explain the behavior or write and test an implementation.

unknownCompose with this

connect

Connect

README tagline: "One MCP for reverse engineering across binaries, applications, and runtime behavior." The agent calls REA through MCP to inspect a local target and trace relevant code; REA returns findings with their evidence, and the agent uses them to explain the behavior or write and test an implementation.

unknownCompose with this

[ Relations ]

Derived alternatives and shared slots

Fills the same slot asExecutor Shared functions code, connect. Can fill the same function slot.
Alternative toAgentMemory Shared functions code, connect. Same kind and overlapping capability.
Fills the same slot asRTK Shared functions code, test. Can fill the same function slot.
Fills the same slot asOnyx Shared functions code, connect, test. Can fill the same function slot.
Fills the same slot aspen.dev Shared functions code, connect. Can fill the same function slot.
Fills the same slot asComparing AI agent sandbox platforms: E2B, Modal, Daytona, and more Shared functions code, connect. Can fill the same function slot.
Fills the same slot asFix Cold Start Latency in AI Sandboxes: Techniques Shared functions code, test. Can fill the same function slot.
Fills the same slot asAI Agent Sandbox Comparison 2026: Seven Platforms Shared functions code, test. Can fill the same function slot.

[ Signals ]

Observed evidence

Each signal carries source, method, and observedAt. Unobserved metrics stay insufficient evidence.

humanCompendium resource card ×3

No social source is stored.

[ Notes ]

No notes are stored.

Frequency in Leyline's observed sample

Why the Score is 7

Publisher-asserted record

Compose the useful parts.

Code

Test

Connect

Derived alternatives and shared slots

Observed evidence