Nexus Agents
未认领Governance substrate for your AI coding agents — adversarial review, drift-detected rules, immutable audit, closed-loop telemetry
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'nexus-agents' -- 'npx' '-y' 'nexus-agents'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
40 个工具中显示 40 个
文档中列出的工具 (40)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
cancel_job
Mark an async-mode job as cancelled — idempotent (#3042 Stage 1b)
ci_health_check
CI infrastructure health — composes GitHub status + recent-runs activity (#3076)
compare_data_feeds
Diff two YAML/JSON feeds: coverage + per-field axes
consensus_vote
Multi-model consensus voting on proposals
create_expert
Create a specialized expert agent
delegate_to_model
Pick the best-fit existing model for a task (no registry change)
execute_expert
Run a task through a previously-created expert (by expertId)
execute_spec
Execute AI software factory spec pipeline
extract_symbols
TypeScript-compiler-API AST symbols from a SINGLE file (functions/classes/types)
get_job_result
Read result of an async-mode dispatch by jobId (#3042 / #2631)
issue_triage
Triage GitHub issues with trust classification
list_experts
Inventory of expert ROLES for createexpert
list_jobs
List async-mode jobs across all tools — cross-session discovery (#3046 / #2631)
list_workflows
Inventory of multi-step TEMPLATES for runworkflow
memory_query
Query across all memory backends
memory_stats
Memory system statistics dashboard
memory_write
Write to typed memory backends
orchestrate
Task orchestration with Orchestrator coordination
query_task_state
Query the structured task-state log for a task ID
query_trace
Query execution traces for observability
registry_import
Draft YAML for a NEW model entry (for picking existing models use delegatetomodel)
repo_analyze
Analyze GitHub repository structure
repo_security_plan
Generate security scanning pipeline for a repo
research_add
Add an arXiv PAPER to the registry (for non-paper sources use researchaddsource)
research_add_source
Add a NON-PAPER source (repo/tool/blog) — for arXiv papers use researchadd
research_analyze
Analyze registry for gaps, trends, coverage
research_catalog_review
Review auto-cataloged research references
research_discover
Discover papers/repos from external sources
research_query
Query research registry (status, overlap, stats, search)
research_synthesize
Synthesize registry into topic clusters with themes
run_dev_pipeline
Full dev pipeline: research, plan, vote, implement, QA
run_graph_workflow
Run a DAG workflow with per-node checkpoints + audit trail (linear → runworkflow)
run_pipeline
Execute a pipeline plugin by name with typed input
run_workflow
Run a linear workflow template (use rungraphworkflow for DAGs)
search_codebase
Cross-file search over declared symbol NAMES (declarations only, not usages)
search_usages
Structural usage/call-site search for a symbol via ast-grep (calls, member calls, new, imports, references) — the "where is X used" gap searchcodebase cannot fill
survey_oss_landscape
Transient OSS project search (license, stars, last-commit) via GitHub
vendor_publishing_audit
Look up a vendor's signing infrastructure (GPG keys, URL patterns, signature shape)
verify_audit_chain
Verify hash chain of a FileAuditStorage audit log directory
weather_report
Multi-CLI performance weather report