Skip to content
ai-supply.store
탐색카테고리리더보드커뮤니티Agent APIFAQ
로그인무료 가입
catalog / Cybersecurity / GhidraMCP
◇MCP serverCybersecurityFree

GhidraMCP

MCP server exposing Ghidra tools so LLMs can decompile and reverse-engineer binaries.

@ai-supply
설치 수59k
↗ 소스 저장소
← More CybersecurityCybersecurity leaderboard →How we grade security →Source ↗

GhidraMCP

ghidraMCP is a Model Context Protocol server that lets LLMs autonomously reverse-engineer binaries by exposing core Ghidra functionality as MCP tools.

Paired with a Ghidra plugin, it can decompile and analyze binaries, list methods, classes, imports and exports, and automatically rename methods and data based on the agent's analysis. This brings AI-assisted reverse engineering and malware analysis into any MCP client.

It is aimed at security researchers, malware analysts, and reverse engineers who want to accelerate binary analysis with an AI assistant.

Rating rank
#1
of 19 in Cybersecurity
Install rank
#9
of 19 in Cybersecurity
Security score
100/100 · A
safe
Security rank
#1
of 19 in Cybersecurity
Installs
59k
cat avg 85k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Cybersecurity leaderboard →
✓ Security: Safe · 100100/100 · grade Ascanned 2h ago

Only compromise signals — malicious or tampered code (leaked secrets, backdoors, path traversal, a dropped executable) — reduce the score. Dangerous-by-capability traits (shell, network, injection strings, pickle) are shown as risk surface: expected for some capabilities — a security tool ships offensive code on purpose — so they do not sink the grade.

Compromise signals
None — no malicious or tampered code detected in the scanned source.
What this capability can do · high confidence (static)
Tools (27)
list_methodslist_classesdecompile_functionrename_functionrename_datalist_segmentslist_importslist_exportslist_namespaceslist_data_itemssearch_functions_by_namerename_variableget_function_by_addressget_current_addressget_current_functionlist_functionsdecompile_function_by_addressdisassemble_functionset_decompiler_commentset_disassembly_commentrename_function_by_addressset_function_prototypeset_local_variable_typeget_xrefs_to
⚑ network
egress → {mcp.settings.host}
Risk surface (7)
External endpoints declaredlowexpected for this capabilityLaurieWired-GhidraMCP-27f316f/.github/workflows/build.yml
1 distinct host(s)
Suspicious network referencesmediumexpected for this capabilityLaurieWired-GhidraMCP-27f316f/README.md
raw IP URL (24 URLs)
Egress to a private/loopback hosthighexpected for this capabilityLaurieWired-GhidraMCP-27f316f/README.md
127.0.0.1
External endpoints declaredlowexpected for this capabilityLaurieWired-GhidraMCP-27f316f/README.md
7 distinct host(s)
Suspicious network referencesmediumexpected for this capabilityLaurieWired-GhidraMCP-27f316f/bridge_mcp_ghidra.py
raw IP URL (2 URLs)
External endpoints declaredlowexpected for this capabilityLaurieWired-GhidraMCP-27f316f/pom.xml
2 distinct host(s)
Vulnerable dependencieshigh
7 known vulnerabilities in: mcp@1.5.0, requests@2.32.3, idna@3.9.0
✔ verified source · pinned LaurieWired-GhidraMCP-27f316f
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/ghidra-mcp-server/check). Click a policy:

OWASP AI control mapping
10passed
3flagged
2runtime-enforced
5governance

Evaluated against the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any control to see the findings.

OWASP Top 10 for LLM Applications
✓LLM01Prompt InjectionPassed
✓LLM02Sensitive Information DisclosurePassed
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 2 pip requirements declared
•Vulnerable dependencies — 7 known vulnerabilities in: mcp@1.5.0, requests@2.32.3, idna@3.9.0 (CWE-1395)
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM05Improper Output HandlingPassed
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s)
•Egress to a private/loopback host — 127.0.0.1 (CWE-918)
•External endpoints declared — 7 distinct host(s)
•External endpoints declared — 2 distinct host(s)
✓LLM07System Prompt LeakagePassed
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
◷LLM10Unbounded ConsumptionRuntime-enforced
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
OWASP Machine Learning Security Top 10
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
⚠ML06AI Supply Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 2 pip requirements declared
•Vulnerable dependencies — 7 known vulnerabilities in: mcp@1.5.0, requests@2.32.3, idna@3.9.0 (CWE-1395)
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
◷ML09Output IntegrityRuntime-enforced
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.

Consume GhidraMCP programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/ghidra-mcp-server

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/ghidra-mcp-server/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add ghidra-mcp-server

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/ghidra-mcp-server/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "ghidra-mcp-server" })
OpenAPI spec →
vlatest
✓ Security: Safe · 1002h ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

무료로 제공하는 보안 검증 AI 역량 — skill, MCP, plugin, agent, 데이터셋을 비롯한 모든 항목에 보안 점수를 매기고 최신성을 추적하며, 사람과 agent 모두를 위해 만들었습니다.

api · v3.1status · all green
문의하기
support@ai-supply.storesecurity@ai-supply.store
카탈로그
  • 탐색
  • 카테고리
  • 리더보드
  • 벤치마크
  • 보안
커뮤니티
  • 커뮤니티
  • FAQ
에이전트용
  • 빠른 시작 (60s)
  • 에이전트 승인
  • Agent API
  • OpenAPI 사양
빌더용
  • 게시
  • 대시보드
계정
  • 계정 만들기
  • 로그인
  • 설정
법적 정보
  • 이용약관
  • 게시자 계약
  • 이용 정책
  • 개인정보 처리방침