Citus MCP

Citus MCP服务器

用于管理Citus分布式PostgreSQL集群的人工智能驱动的MCP服务器

](https://golang.org)   

快速开始 • 特性 • 安装 • 配置 • 工具参考 • 示例

______________________________________________________________________

📖 什么是Citus MCP？

Citus MCP是一家 模型上下文协议（MCP） 服务器，使GitHub Copilot等AI助手能够与您的Citus分布式PostgreSQL集群进行交互。它提供：

运作原理

┌─────────────────┐                      ┌──────────────┐                ┌─────────────────┐
│  GitHub Copilot │     MCP Protocol     │  citus-mcp   │      SQL       │  Citus Cluster  │
│  (VS Code/CLI)  │  │    server    │  │  (Coordinator)  │
└─────────────────┘      stdio/SSE       └──────────────┘                └─────────────────┘

______________________________________________________________________

🚀 快速开始

先决条件

• 转到1.23+ （从源头建设）
• PostgreSQL 13–17 在协调器上使用Citus扩展名（11.x或更高版本）
• GitHub Copilot 支持MCP（VS代码或CLI）

1.构建服务器

git clone https://github.com/citusdata/citus-mcp.git
cd citus-mcp
make build
# Binary created at ./bin/citus-mcp

或者直接使用Go：

go build -o bin/citus-mcp ./cmd/citus-mcp

2.配置您的连接

在以下位置创建配置文件 ~/.config/citus-mcp/config.yaml:

# Minimum required configuration
coordinator_dsn: postgres://username:password@localhost:5432/mydb?sslmode=disable

或者设置环境变量：

export CITUS_MCP_COORDINATOR_DSN="postgres://username:password@localhost:5432/mydb?sslmode=disable"

3.设置VS代码

创建 .vscode/mcp.json 在您的工作区（或 mcp.json 在项目根节点）：

{
  "mcpServers": {
    "citus-mcp": {
      "command": "/path/to/citus-mcp/bin/citus-mcp",
      "args": [],
      "env": {
        "CITUS_MCP_COORDINATOR_DSN": "postgres://username:password@localhost:5432/mydb?sslmode=disable"
      }
    }
  }
}

4.测试连接

在VS Code Copilot Chat中，键入：

@citus-mcp ping

您应该看到一个“pong”响应，确认连接正常。

______________________________________________________________________

✨ 特性

71个MCP工具，涵盖诊断、取证、容量规划、顾问、， 警报、时间序列和门控执行操作。单一覆盖工具 citus_full_report 一次性运行约30个只读诊断程序 总体健康状况、主要发现和具体建议。

查看完整 工具参考 下面是参数和详细信息。

🧭 报告和覆盖工具

🔍 集群检查（只读）

📊 监控和活动

🧠 内存和容量规划

🛠️ MX和节点添加

🚑 取证与恢复

🔧 元数据、扩展和路由

🤖 智能顾问

🚨 警报

📈 时间序列和快照

⚡ 执行操作（需要批准）

______________________________________________________________________

📦 安装

选项1：从源代码构建

# Clone the repository
git clone https://github.com/citusdata/citus-mcp.git
cd citus-mcp

# Build using Make
make build

# Or build directly with Go
go build -o bin/citus-mcp ./cmd/citus-mcp

# (Optional) Install to your PATH
sudo cp bin/citus-mcp /usr/local/bin/

选项2：去安装

go install github.com/citusdata/citus-mcp/cmd/citus-mcp@latest

验证安装

citus-mcp --help

______________________________________________________________________

⚙️ 配置

连接字符串（DSN）

最重要的配置是PostgreSQL与Citus协调器的连接字符串：

postgres://[user]:[password]@[host]:[port]/[database]?sslmode=[mode]

示例：

# Local development (no SSL)
postgres://postgres:secret@localhost:5432/mydb?sslmode=disable

# Production with SSL
postgres://admin:secret@citus-coord.example.com:5432/production?sslmode=require

# With specific schema
postgres://user:pass@host:5432/db?sslmode=require&search_path=myschema

配置方法

配置可以通过以下方式提供（按优先级顺序）：

1. 命令行标志
2. 环境变量
3. 配置文件

方法1：环境变量

# Required
export CITUS_MCP_COORDINATOR_DSN="postgres://user:pass@localhost:5432/mydb?sslmode=disable"

# Optional
export CITUS_MCP_MODE="read_only"           # read_only (default) or admin
export CITUS_MCP_ALLOW_EXECUTE="false"      # Enable execute operations
export CITUS_MCP_APPROVAL_SECRET="secret"   # Required if allow_execute=true
export CITUS_MCP_LOG_LEVEL="info"           # debug, info, warn, error

方法2：配置文件

创建 ~/.config/citus-mcp/config.yaml:

# ===========================================
# Citus MCP Server Configuration
# ===========================================

# Database Connection (REQUIRED)
# -----------------------------
coordinator_dsn: postgres://user:password@localhost:5432/mydb?sslmode=disable

# Optional: Override credentials from DSN
# coordinator_user: myuser
# coordinator_password: mypassword

# Connection Mode (RECOMMENDED: true for production)
# --------------------------------------------------
# When true (default), worker data is fetched via run_command_on_workers() UDF.
# Set to false only for dev/test with direct worker access.
coordinator_only: true

# Optional: Direct worker connections (dev/test override only)
# If specified when coordinator_only=true, these take precedence (dev escape hatch)
# worker_dsns: postgres://user:pass@worker1:5432/db,postgres://user:pass@worker2:5432/db

# Server Mode
# -----------
# read_only: Only inspection tools available (default, safest)
# admin: All tools available including execute operations
mode: read_only

# Execute Operations (only if mode=admin)
# ---------------------------------------
allow_execute: false
# approval_secret: your-secret-key  # Required if allow_execute=true

# Performance Settings
# --------------------
cache_ttl_seconds: 5          # Cache duration for metadata queries
enable_caching: true          # Set to false to disable caching
max_rows: 200                 # Maximum rows returned per query
max_text_bytes: 200000        # Maximum text size in responses

# Timeouts
# --------
connect_timeout_seconds: 10   # Connection timeout
statement_timeout_ms: 30000   # Query timeout (30 seconds)

# Logging
# -------
log_level: info               # debug, info, warn, error

# Transport (NEW)
# ---------------
# stdio: Standard input/output (default, for VS Code/CLI integration)
# sse: Server-Sent Events over HTTP (for remote/network access)
# streamable: Streamable HTTP transport (for remote/network access)
transport: stdio

# HTTP Settings (only used when transport is sse or streamable)
# http_addr: 127.0.0.1        # Listen address (use 0.0.0.0 for all interfaces)
# http_port: 8080             # Listen port
# http_path: /mcp             # Endpoint path
# sse_keepalive_seconds: 30   # SSE keepalive interval

方法3：命令行标志

# Using flags (note: use underscores in flag names)
bin/citus-mcp --coordinator_dsn "postgres://..." --mode read_only

# Using positional argument for DSN
bin/citus-mcp "postgres://user:pass@localhost:5432/mydb?sslmode=disable"

# Specify config file
bin/citus-mcp --config /path/to/config.yaml

# Start with SSE transport
bin/citus-mcp --transport sse --http_port 8080 --coordinator_dsn "postgres://..."

配置文件位置

服务器按以下顺序搜索配置文件：

1. --config / -c 旗帜
2. CITUS_MCP_CONFIG 环境变量
3. $XDG_CONFIG_HOME/citus-mcp/config.yaml
4. ~/.config/citus-mcp/config.yaml
5. ./citus-mcp.yaml （当前目录）

支持的格式：YAML、JSON、TOML

______________________________________________________________________

🌐 运输选项

Citus MCP支持三种不同部署场景的传输模式：

1.标准运输（默认）

标准输入/输出传输——服务器通过stdin/stdout进行通信。这是默认设置，用于与VS Code和GitHub Copilot CLI直接集成。

# Default - stdio transport
bin/citus-mcp --coordinator_dsn "postgres://..."

# Explicit
bin/citus-mcp --transport stdio --coordinator_dsn "postgres://..."

使用案例：

• VS代码复制聊天集成
• GitHub Copilot 命令行工具
• 本地开发

2.SSE传输（服务器发送事件）

使用服务器发送事件的基于HTTP的传输。服务器作为HTTP守护进程运行，客户端可以远程连接。

# Start server on HTTP with SSE
bin/citus-mcp --transport sse --http_addr 0.0.0.0 --http_port 8080 --coordinator_dsn "postgres://..."

# Or via environment variables
export CITUS_MCP_TRANSPORT=sse
export CITUS_MCP_HTTP_ADDR=0.0.0.0
export CITUS_MCP_HTTP_PORT=8080
export CITUS_MCP_COORDINATOR_DSN="postgres://..."
bin/citus-mcp

终点：

• GET /mcp -建立SSE连接
• POST /mcp/session/{id} -向会话发送消息
• GET /health -健康检查

使用案例：

• 远程MCP服务器部署
• Docker/Kubernetes部署
• 多个客户端的共享服务器
• 网络可访问的MCP服务

3.流式HTTP传输

支持流媒体的现代HTTP传输。建议用于新部署。

# Start server with streamable HTTP transport
bin/citus-mcp --transport streamable --http_addr 0.0.0.0 --http_port 8080 --coordinator_dsn "postgres://..."

终点：

• POST /mcp -使用流式响应处理MCP请求
• GET /health -健康检查

使用案例：

• 与SSE相同，具有更好的流媒体支持
• SSE不理想的环境

Docker部署示例

FROM golang:1.22-alpine AS builder
WORKDIR /app
COPY . .
RUN go build -o citus-mcp ./cmd/citus-mcp

FROM alpine:latest
COPY --from=builder /app/citus-mcp /usr/local/bin/
EXPOSE 8080
CMD ["citus-mcp", "--transport", "sse", "--http-addr", "0.0.0.0", "--http-port", "8080"]

# docker-compose.yml
version: '3.8'
services:
  citus-mcp:
    build: .
    ports:
      - "8080:8080"
    environment:
      CITUS_MCP_TRANSPORT: sse
      CITUS_MCP_HTTP_ADDR: 0.0.0.0
      CITUS_MCP_HTTP_PORT: 8080
      CITUS_MCP_COORDINATOR_DSN: postgres://user:pass@citus-coordinator:5432/mydb?sslmode=disable

连接到远程服务器

对于SSE/Streamable传输，请将MCP客户端配置为通过HTTP连接：

{
  "mcpServers": {
    "citus-mcp": {
      "type": "sse",
      "url": "http://citus-mcp-server:8080/mcp"
    }
  }
}

______________________________________________________________________

🔌 使用GitHub Copilot进行设置

VS代码设置

1. 安装先决条件

- 带有GitHub Copilot扩展的VS代码 - 在副驾驶设置中启用MCP支持

1. 创建MCP配置

创建 .vscode/mcp.json 在您的工作空间中：

   {
     "mcpServers": {
       "citus-mcp": {
         "command": "/absolute/path/to/bin/citus-mcp",
         "args": [],
         "env": {
           "CITUS_MCP_COORDINATOR_DSN": "postgres://user:pass@localhost:5432/mydb?sslmode=disable"
         }
       }
     }
   }

或用于开发（使用 go run):

   {
     "mcpServers": {
       "citus-mcp": {
         "command": "go",
         "args": ["run", "./cmd/citus-mcp"],
         "cwd": "/path/to/citus-mcp",
         "env": {
           "CITUS_MCP_COORDINATOR_DSN": "postgres://user:pass@localhost:5432/mydb?sslmode=disable"
         }
       }
     }
   }

1. 重新加载VS代码 并打开Copilot聊天

1. 验证连接

   @citus-mcp ping

GitHub Copilot命令行界面设置

1. 创建全局MCP配置

创建 ~/.config/github-copilot/mcp.json:

   {
     "mcpServers": {
       "citus-mcp": {
         "command": "/usr/local/bin/citus-mcp",
         "args": [],
         "env": {
           "CITUS_MCP_COORDINATOR_DSN": "postgres://user:pass@localhost:5432/mydb?sslmode=disable"
         }
       }
     }
   }

1. 验证设置

   copilot mcp list
   copilot mcp test citus-mcp

1. 在CLI中使用

   copilot -p "Show me the cluster summary"

______________________________________________________________________

💡 使用示例

以下示例是您可以在Copilot中输入的自然语言提示 聊天（VS代码/CLI）。Copilot将它们映射到底层MCP工具调用； JSON有效载荷显示在对自动化有用的地方。

基本集群检查

@citus-mcp Give me everything about this cluster

→ citus_cluster_summary 随着 {"all": true} --返回协调器/工作器拓扑、计数、GUC、配置报告和跨工具健康汇总（内存/连接/漂移/元数据同步/操作）。

@citus-mcp List all distributed and reference tables

→ citus_list_distributed_tables, citus_list_reference_tables

@citus-mcp Inspect the public.orders table including shards and indexes

→ citus_table_inspector 随着 {"table":"public.orders","include_shards":true,"include_indexes":true}

监控

@citus-mcp Show current cluster activity
@citus-mcp Are there any lock waits right now?
@citus-mcp Show background job progress
@citus-mcp Proactive health dashboard for the cluster

→ citus_activity, citus_lock_inspector, citus_job_inspector, citus_proactive_health

内存和容量规划

@citus-mcp Project per-backend Citus metadata cache memory

→ citus_metadata_cache_footprint --尺寸 MetadataCacheMemoryContext 基于当前形状的每个后端。

@citus-mcp Estimate PG CacheMemoryContext footprint on the coordinator and each worker

→ citus_pg_cache_footprint --relcache/catcache/plancache估计值。

@citus-mcp Is the cluster close to OOM? Use worst_case=true and 64 GiB per node

→ citus_memory_risk_report 随着 {"worst_case":true, "node_ram_bytes":68719476736} --13项预算（共享缓冲区、wal_buffers、锁/预锁表、wal发送方、逻辑解码、bgworker基线、每个后端进程基线+计划缓存、Citus元数据+PG CacheMemoryContext、， work_mem × hash_mem_multiplier × (1 + parallel_workers_per_gather) × plan_ops_per_query、温度缓冲、自动真空、低温↔worker libpq缓冲区）与节点RAM进行比较。

@citus-mcp Sample PostgreSQL MemoryContextStats on every node

→ citus_worker_memcontexts --现场直播 pg_get_backend_memory_contexts() 在集群中散开。

@citus-mcp What will happen to memory if I double the number of monthly partitions?

→ citus_partition_growth_simulator 随着 {"partitions_per_parent":24}

@citus-mcp How many clients can each node handle? Compare coord-only, MX, and PgBouncer

→ citus_connection_capacity --在每种部署模式下返回有效的最大客户端后端以及瓶颈解释。

@citus-mcp Simulate 400 concurrent multi-shard queries and tell me when max_shared_pool_size saturates

→ citus_connection_fanout_simulator 随着 {"concurrent_clients":400}

@citus-mcp Should I use PgBouncer session or transaction mode with this workload?

→ citus_pooler_advisor

@citus-mcp Size hardware for 5× projected load: 50k IOPS, 2 TB data, 200 active clients

→ citus_hardware_sizer 随着 {"projected_data_gb":2000,"projected_active_clients":200,"projected_iops":50000}

@citus-mcp Is 32 shards the right number? Chart the trade-offs

→ citus_shardcount_tradeoff_chart

MX和节点添加

@citus-mcp Run pre-flight checks for adding a worker at newworker.prod:5432

→ citus_add_node_preflight 随着 {"host":"newworker.prod","port":5432} --协调方检查表（扩展、类型、模式、角色、版本匹配、， max_locks_per_transaction/max_worker_processes/max_connections 地板， wal_level=logical，复制插槽）。

@citus-mcp Advise how to prepare newworker.prod:5432 before I call citus_add_node and generate a shell script

→ citus_node_prepare_advisor 随着 {"host":"newworker.prod","port":5432,"generate_script":true}

@citus-mcp Will metadata sync succeed on the new node, or should I use nontransactional mode? Target has 16 GiB RAM

→ citus_metadata_sync_risk 随着 {"target_node_ram_gib":16} --DDL计数、tx锁定、持续时间、超时相关性。

@citus-mcp Is the cluster ready for MX with 2 concurrent queries per peer and new nodes sized at max_connections=300?

→ citus_mx_readiness 随着 {"concurrent_queries_per_peer":2,"new_node_max_connections":300,"expected_clients_per_node":100}

@citus-mcp Which existing worker should I snapshot from when adding a new one?

→ citus_snapshot_source_advisor

元数据、扩展和路由

@citus-mcp Deep metadata consistency check across every node

→ citus_metadata_health 随着 {"check_level":"deep","include_fixes":true}

@citus-mcp Are all extensions at the same version on every node?

→ citus_extension_drift_scanner

@citus-mcp Measure planner overhead across the cluster

→ citus_planner_overhead_probe

@citus-mcp Detect routing drift — are any queries landing on the wrong shard?

→ citus_routing_drift_detector

@citus-mcp Run a synthetic probe to validate end-to-end correctness

→ citus_synthetic_probe

@citus-mcp Dump the session's active guardrails (statement timeout, read-only, row caps)

→ citus_session_guardrails

顾问（只读建议）

@citus-mcp Run the Citus advisor focused on skew and include SQL fixes

→ citus_advisor 随着 {"focus":"skew","include_sql_fixes":true}

@citus-mcp Analyze configuration, all categories, warn level and above

→ citus_config_advisor 随着 {"severity_filter":"warning"}

@citus-mcp Deep inspection of PostgreSQL + Citus GUCs

→ citus_config_deep_inspect

@citus-mcp Advise on shard count per distributed table given current/projected load

→ citus_shard_advisor

@citus-mcp Which tables would benefit from columnar storage?

→ citus_columnar_advisor

@citus-mcp Show risky tenants (heavy shards, hot locks, outsized query share)

→ citus_tenant_risk

@citus-mcp Investigate which queries are pathological (cross-shard joins, broadcasts, repartitions)

→ citus_query_pathology

@citus-mcp Inspect the connected PgBouncer for pool health

→ citus_pgbouncer_inspector

碎片和偏斜分析

@citus-mcp Skew report for the orders table by row count
@citus-mcp Heatmap of the hottest shards in the last interval

→ citus_shard_skew_report, citus_shard_heatmap

@citus-mcp Estimate the cost (time, WAL, bytes) of rebalancing the current cluster

→ citus_rebalance_cost_estimator

时间序列/快照

@citus-mcp Record a snapshot named pre-deploy-2026-04
@citus-mcp List snapshots taken in the last 30 days
@citus-mcp Trend query latency over the last 7 days
@citus-mcp Detect regressions against the pre-deploy-2026-04 snapshot
@citus-mcp Project 12-month growth from snapshots
@citus-mcp What changed between snapshots A and B?

→ citus_snapshot_record, citus_snapshot_list, citus_trend, citus_regression_detect, citus_growth_projection, citus_what_changed

警报

@citus-mcp List open alarms
@citus-mcp Acknowledge alarm abc-123
@citus-mcp Clear all resolved alarms older than 7 days

→ citus_alarms_list, citus_alarms_ack, citus_alarms_clear

执行操作（需要批准）

@citus-mcp Plan a rebalance limited to 10 shard moves
@citus-mcp Request an approval token for rebalance
@citus-mcp Execute rebalance with token 
@citus-mcp Check rebalance status

→ citus_rebalance_plan → citus_request_approval_token → citus_rebalance_execute → citus_rebalance_status

@citus-mcp Move shard 102008 from 10.0.0.5:5432 to 10.0.0.6:5432

→ citus_move_shard_plan + citus_move_shard_execute （带批准标志）

@citus-mcp Isolate tenant 42 to its own shard
@citus-mcp Clean up orphaned shard placements left by a failed move

→ citus_isolate_tenant, citus_cleanup_orphaned

______________________________________________________________________

📚 工具参考

以下所有工具名称都可以作为MCP工具调用直接调用。大多数 接受具有所列参数的可选对象； — 指工具 不接受任何输入。

🧭 报告和覆盖工具

示例-- citus_full_report:

// Default invocation: runs all read-only diagnostics with sensible defaults
{}

// With partition what-if and a tighter memory budget
{
  "partition_growth_factor": 2.0,
  "memory_budget_bytes": 4294967296
}

// Include optional synthetic probe + raw per-tool outputs (verbose)
{
  "synthetic_probe": true,
  "include_verbose_outputs": true
}

岩芯检查（只读）

监控和活动

内存和容量规划

MX/节点添加

取证与恢复

示例-- citus_rebalance_forensics:

// Default: find most recent stuck/running job within last 24h
{}

// Diagnose a specific job, include finished tasks for postmortem
{"job_id": 42, "include_finished_tasks": true}

// Tighter thresholds: flag retries earlier, warn on smaller cleanup backlogs
{"retries_exhausted_threshold": 1, "cleanup_backlog_threshold": 10}

| citus_placement_integrity_check | schemas? （默认值 ["public"]), skip_size_drift?, size_drift_factor? （默认值2.0）， max_rows_per_class? （默认值200）， check_inactive_placements? （默认为true）|Citus元数据之间的三向交叉检查(pg_dist_placement × pg_dist_shard × pg_dist_node)，每个工作者的磁盘现实(pg_class 扫描通过 run_command_on_workers 禁用Citus分片可见性挂钩），以及 pg_dist_cleanup.检测：（a） ghost_placements --元数据引用磁盘上缺少的分片（读取WILL错误）；b 孤儿表 --没有放置行的workers上的分片后缀表（标记是否排队 pg_dist_cleanupc 无数据无效 — shardstate != 1 但数据仍然存在；d 尺寸_漂移 — pg_relation_size 对比 placement.shardlength 偏离> size_drift_factore 跟踪统计 — placement.shardlength = 0 但是磁盘有数据（默默地导致重新平衡器做出错误的决定；用修复 SELECT citus_update_shard_statistics(shardid) 或 citus_update_table_statistics(relname)).孤儿分类匹配 (base_name, shardid) 对元数据（不仅仅是基名称）进行配对，因此用户表像 events_123456 没有匹配的shardid不会被标记。 权衡： 如果一个分片被完全删除（放置行消失了，从未排队等待清理），但其磁盘上的表仍然存在，则配对匹配器不会将其检测为孤立分片——use SELECT run_command_on_workers($$SELECT oid::regclass FROM pg_class WHERE relname ~ '_[0-9]+$'$$); 就像用皮带和牙套清扫那个箱子一样。扇出失败的工人名单如下 skipped_workers[] 随着 partial_results=true；对这些节点抑制重影检测，以避免误报关键警报。发布每个班级的和解剧本(citus_copy_shard_placement / citus_cleanup_orphaned_resources / citus_update_shard_statistics)和警报(placement.ghost, placement.orphan_tables, placement.inactive_with_data, placement.stale_stats, placement.partial_results).只读。 |

示例-- citus_placement_integrity_check:

// Default — scan public schema, detect all 4 classes
{}

// Multi-schema, skip size drift for speed
{"schemas": ["public", "tenants"], "skip_size_drift": true}

// Strict size drift (flag any > 1.5× deviation)
{"size_drift_factor": 1.5}

示例-- citus_2pc_recovery_inspector:

// Default — detect commit_needed / rollback_needed / in_flight / foreign_initiator
{}

// Aggressive: treat anything >10s as orphan, escalate orphans older than 2 min
{"in_flight_threshold_seconds": 10, "stuck_orphan_seconds": 120}

// Compact output (no recovery script)
{"suppress_recovery_script": true}

// Include non-citus GIDs in the output (e.g. for third-party 2PC coordinators)
{"include_non_citus": true}

元数据/扩展/路由

顾问（只读）

警报

时间序列/快照

执行操作（需要批准令牌）

______________________________________________________________________

📋 内置提示

在Copilot Chat中使用以下提示进行指导工作流程：

______________________________________________________________________

🔐 安全

只读模式（默认）

默认情况下，citus mcp在 只读模式这意味着：

• ✅ 所有检查和监控工具均正常工作
• ✅ 顾问提供建议
• ❌ 执行操作已禁用
• ❌ 无法修改任何数据

带有批准令牌的管理模式

要启用执行操作，请执行以下操作：

1. 设置管理模式 在配置中：

   mode: admin
   allow_execute: true
   approval_secret: your-secret-key-here

1. 请求批准令牌 执行前：

   @citus-mcp Request approval token for rebalance

1. 使用令牌 在执行命令中：

   @citus-mcp Execute rebalance with token: 

令牌是有时间限制的，并且特定于操作（HMAC签名）。

______________________________________________________________________

🔧 故障排除

连接问题

错误： connection refused

• 验证协调器主机和端口是否正确
• 检查PostgreSQL是否正在运行并接受连接
• 确保防火墙规则允许连接

错误： authentication failed

• 验证DSN中的用户名和密码
• 检查用户是否具有数据库权限
• 对于SSL问题，请尝试 sslmode=disable 用于本地测试

MCP问题

副驾驶看不到citus mcp

• 确保 mcp.json 位置正确
• 检查命令路径是否为绝对路径
• 更改配置后重新加载VS代码

工具返回错误

• 检查日志： CITUS_MCP_LOG_LEVEL=debug bin/citus-mcp
• 验证是否安装了Citus扩展： SELECT * FROM pg_extension WHERE extname = 'citus'

测试连接

# Test directly
CITUS_MCP_COORDINATOR_DSN="postgres://..." bin/citus-mcp

# Then send a ping via stdin
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | bin/citus-mcp

______________________________________________________________________

🛠️ 发展

运行测试

# Unit tests
make test

# With verbose output
go test -v ./...

# Integration tests (requires Docker)
make docker-up
make integration
make docker-down

代码检查

make lint

项目结构

citus-mcp/
├── cmd/citus-mcp/       # Main entry point
├── internal/
│   ├── mcpserver/       # MCP server implementation
│   │   ├── tools/       # Tool implementations (71 tools)
│   │   ├── prompts/     # Prompt templates
│   │   └── resources/   # Static resources
│   ├── db/              # Database layer and worker management
│   ├── citus/           # Citus-specific logic and queries
│   │   ├── advisor/     # Advisor implementations
│   │   └── guc/         # GUC (configuration) analysis
│   ├── cache/           # Query result caching
│   ├── config/          # Configuration management
│   ├── errors/          # Error types and codes
│   ├── fanout/          # Parallel query execution
│   ├── logging/         # Structured logging
│   └── safety/          # Guardrails and approval tokens
├── docker/              # Docker Compose setup for testing
├── docs/                # Additional documentation
└── tests/               # Integration tests

______________________________________________________________________

🤝 贡献

欢迎投稿！请参阅 贡献.md 作为指导方针。

______________________________________________________________________

📄 许可证

MIT许可证——见 许可证 了解详情。

______________________________________________________________________

⬆ 返回顶部

制作❤️ 为Citus社区