CodeBro MCP server
2026년 10월 31일 커밋Provides AI coding agents with persistent engineering memory, verified repository facts, impact analysis, and guarded transactional changes.
다른 이름 EffNine/CodeBro
- 스타
- 1
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 10월 31일
- 라이선스
- MIT
CodeBro MCP란?
CodeBro은(는) MCP server입니다. Provides AI coding agents with persistent engineering memory, verified repository facts, impact analysis, and guarded transactional changes.
프로젝트 README에서 생성된 요약
CodeBro MCP server 정보
Providing AI coding agents with persistent engineering memory and verified repository facts is what CodeBro enables for developers using tools like Claude Code, Cursor, or OpenCode. It functions as an engineering intelligence runtime that sits between your host agent and your codebase to prevent agents from repeatedly rediscovering project structures or forgetting critical decisions between sessions. The server operates via stdio and can connect to upstream providers through a Conductor using HTTP and Bearer keys.
CodeBro distinguishes itself by maintaining three distinct levels of information trust: high-confidence verified facts generated via tree-sitter scans, medium-high engineering decisions authored by humans, and low-confidence agent-recorded memory. It offers specialized tools for guarded changes, such as multi-file all-or-nothing transactions with rollback capabilities, and sandboxed execution evidence that includes git revisions and exit codes. Users initialize the system with the codebro init command to scan their workspace into a local facts file, ensuring the agent has a deterministic understanding of the project identity and constraints.
활용 사례
- 1Maintain persistent project knowledgeAn AI agent can record and recall engineering decisions so it does not lose context across different coding sessions.
- 2Execute safe code mutationsDevelopers can instruct an agent to perform multi-file updates that automatically roll back if the transaction fails.
- 3Verify command execution resultsAn agent can run builds or tests in a sandbox and receive a full report including the environment and reproducibility details.
- 4Perform architectural consultationsUsers can query the system to get expert opinions on debugging or architecture through the Conductor interface.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
자동 검사
2026년 11월 15일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능effnine/codebro is public and reachablegithub.com/effnine/codebro ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-10-31github.com/effnine/codebro ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음0 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기CodeBro
CodeBro is an MCP-based engineering intelligence runtime that provides AI coding agents with repository understanding, verified facts, engineering memory, impact analysis, guarded changes, and reproducible execution evidence.
AI coding agents are good at reasoning, but they repeatedly rediscover project structure and forget engineering decisions across sessions. CodeBro solves this by maintaining verified facts and recorded memory that persist between sessions.
Architecture and module map: ARCHITECTURE.md.
AI Coding Agents
OpenCode · Claude Code · Codex · Cursor
│
MCP
▼
┌───────────┐
│ CodeBro │
├───────────┤
│ Facts │
│ Memory │
│ Identity │
│ Impact │
│ Guarded │
│ Changes │
│ Evidence │
│ Consultant│
└─────┬─────┘
│
ConsultantProvider
│
▼
Conductor
(HTTP + Bearer key)
│
routing / scoring / health
│
▼
Upstream providers
Host agent owns: reasoning, planning, tool selection, execution strategy, UX. CodeBro owns: project identity, verified project facts, persistent engineering memory, impact analysis, guarded/transactional mutations, sandboxed execution evidence, and consultant queries via Conductor.
CodeBro is not:
- a replacement coding agent
- a TUI or chat assistant
- a model provider
- a generic shell / filesystem / Git MCP
- an autonomous agent loop
The frozen v1 tool contract is documented in
docs/MCP_API_V1.md; the historical design narrative
lives in docs/design/MCP_SERVER.md.
Quick Start
git clone https://github.com/EffNine/CodeBro.git
cd CodeBro
cargo install --path crates/mcp-server # binary name: codebro
# From a target project:
codebro init # scan the workspace into .codebro/facts.json
codebro doctor # verify the runtime state
opencode mcp add codebro -- "$(which codebro) serve"
For a complete Conductor setup guide, see docs/CONDUCTOR_HOWTO.md.
What CodeBro Provides (24 tools: v1 contract of 17 + 8 additive − 1 removed)
| Surface | Tools | Purpose |
|---|---|---|
| Orientation | workspace_context, repository_health |
Project identity, fact counts, workspace diagnostics |
| Verified facts | engineering_facts, reindex |
Relevance-ranked retrieval over the validated fact graph (impact evidence arrives via the brief's embedded traversal) |
| Engineering memory | engineering_memory, memory_stats, record_memory, delete_memory |
Persistent, trust-aware agent-recorded memory (never promoted into facts) |
| Identity | update_identity |
Declared-intent store: constraints, decisions, roadmap |
| Guarded changes | apply_change, apply_changes |
Single-file guarded mutation; multi-file all-or-nothing transaction with rollback |
| Execution evidence | sandbox_status, sandbox_exec, sandbox_test, sandbox_build |
Policy-gated commands with full evidence envelopes (git revision, exit code, reproducibility, environment) |
| Consultant | consult |
Ask Conductor-backed providers for architecture/debug/review opinions |
| Persistent context | context, remember, forget, recall |
Always-available context packet; confirmed user context with provenance; query-driven history |
| Learning & skills | learn, skill, task |
Cautious hypotheses; human-approved skill registry with reuse/evolution detectors; durable task runtime |
| Decision support | engineering_brief |
Bounded deterministic brief for planning |
Trust Model
Three distinct classes of information — never blurred:
| Class | Source | Trust |
|---|---|---|
| Verified facts | codebro init (tree-sitter scan) |
High — deterministic, validated (0-issue store) |
| Engineering decisions | Human-authored identity/constraints | Medium-high — declared intent |
| Agent-recorded memory | Agents calling record_memory |
Low — unverified, self-declared confidence |
Agent-recorded memory is never promoted to the verified fact store.
Jev Advisory (informational only, off by default)
CodeBro can attach a non-authoritative Jev escalation note to skill approval
requests. Jev never approves, denies, executes, or changes policy — the
deterministic needs_input verdict is computed first, and the observer runs
detached with its outcome discarded.
- Baseline:
jev-baseline-1(jev-1.13.0, question set v3, confidence ≥ 0.80, escalation-only). Any baseline drift disables advisory automatically. - Flags (both default
false):JEV_SHADOW_ENABLED,JEV_ADVISORY_ENABLED. Both off means zero Jev calls and unchanged behavior. - Output:
JEV ADVISORY: … Informational only.tracing line plus structured telemetry in.codebro/jev-advisory.jsonl. Rollback isJEV_ADVISORY_ENABLED=false.
Details: docs/JEV_ADVISORY.md.
Installation
Requires a Rust toolchain (see rust-toolchain.toml).
cargo build --release
cargo install --path crates/mcp-server
CLI
codebro init # Scan workspace → .codebro/facts.json
codebro doctor # Diagnostics (exit 0 ok / 1 warn / 2 error)
codebro serve # MCP server over stdio
codebro facts diff # Diff current repo state vs last index + impact projection
codebro list-models # List models from configured provider
codebro consult # Ask Conductor a question directly
codebro auth status # Check consultant provider auth
codebro context # Bounded context packet (host/hook surface, read-only)
codebro export # Export portable memory (records, history, skills)
codebro import # Import a portable memory export (verified, redacted)
Portable memory is explicit and safe: codebro export --out <dir> writes a
versioned, secret-redacted manifest + JSONL bundle; `codebro import --file
Links
- Frozen v1 MCP Contract
- v1.1.0 Release Notes
- v1.0.0 Release Notes
- Conductor Setup HOWTO
- Architecture Decision Records
- Changelog
- License
Current public release: v1.1.0.
The former chat TUI is preserved on the tui-legacy branch; the development
line is MCP-first only.
CodeBro MCP 질문
Can CodeBro perform multi-file changes?
Yes, it supports multi-file all-or-nothing transactions with rollback capabilities.