
swipl-mcp-server
This server lets tools-enabled LLMs work directly with SWI‑Prolog. It supports loading Prolog files, adding/removing facts and rules, listing symbols, and running queries with two modes: deterministic pagination and true engine backtracking.
README
SWI-Prolog MCP Server
An MCP server that lets tools-enabled LLMs work directly with SWI‑Prolog. It supports loading Prolog files, adding/removing facts and rules, listing symbols, and running queries with two modes: deterministic pagination and true engine backtracking.
Requirements
- Node.js ≥ 18.0.0
- SWI‑Prolog installed and available in PATH
Quick Start
# Run directly with npx (no installation required)
npx @vpursuit/swipl-mcp-server
Claude Desktop (basic)
{
"mcpServers": {
"swipl": {
"command": "npx",
"args": ["@vpursuit/swipl-mcp-server"]
}
}
}
Optional timeouts (development):
{
"mcpServers": {
"swipl": {
"command": "npx",
"args": ["@vpursuit/swipl-mcp-server"],
"env": {
"SWI_MCP_READY_TIMEOUT_MS": "10000",
"SWI_MCP_QUERY_TIMEOUT_MS": "120000",
"MCP_LOG_LEVEL": "debug",
"DEBUG": "swipl-mcp-server"
}
}
}
}
MCP Inspector
npx @modelcontextprotocol/inspector --transport stdio npx @vpursuit/swipl-mcp-server
Configuration file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%/Claude/claude_desktop_config.json
Configuration
Environment Variables
Configure timeouts, logging, and behavior via environment variables:
SWI_MCP_READY_TIMEOUT_MS
: server startup timeout (ms), default 5000SWI_MCP_QUERY_TIMEOUT_MS
: query execution timeout (ms), default 30000MCP_LOG_LEVEL
:debug
|info
|warn
|error
|silent
(defaultwarn
)DEBUG
: enable debug logs, set toswipl-mcp-server
SWI_MCP_TRACE
: optional low-level trace of child I/O and protocolSWI_MCP_PROLOG_PATH
: override Prolog server script path
Tools
- Core:
help
,license
,capabilities
- Database:
db_load
,db_assert
,db_retract
,db_dump
- Query:
query_start
,query_startEngine
,query_next
,query_close
- Symbols:
symbols_list
Examples
- Load and query:
db_load { filename: "family.pl" }
query_start { query: "parent(X, mary)" }
→query_next()
until no more solutions →query_close()
- Engine mode:
query_startEngine { query: "member(X, [1,2,3])" }
→query_next()
repeatedly →query_close()
See docs/examples.md for many more, including arithmetic, list ops, collections, and string/atom helpers.
Architecture
- Single persistent SWI‑Prolog process with two query modes (standard via
call_nth/2
, engine via SWI engines) - Term-based wire protocol: Node wraps requests as
cmd(ID, Term)
, replies asid(ID, Reply)
; back‑compatible with bare terms - Hybrid security model with library(sandbox) validation and explicit blacklist; guarded consultation of files
Details: see docs/architecture.md.
Troubleshooting
- “Prolog not found”: ensure
swipl --version
works; SWI‑Prolog must be in PATH - Startup timeout: increase
SWI_MCP_READY_TIMEOUT_MS
- Query timeout: increase
SWI_MCP_QUERY_TIMEOUT_MS
- Session conflicts: close current session before starting a different mode
error(unsafe_goal(...))
: your query uses blocked predicates; see Security- Custom script path: set
SWI_MCP_PROLOG_PATH
Development
- Install deps:
npm install
- Build:
npm run build
- Run dev server:
npm run server
- Tests:
npm test
(see CONTRIBUTING.md for details)
Publishing and release workflows are documented in docs/deployment.md.
Contributing
See CONTRIBUTING.md for local setup, workflow, and the PR checklist.
For security practices, reporting, and hardening guidance, see SECURITY.md.
Further reading:
- docs/architecture.md — components, modes, and wire protocol
- docs/deployment.md — release, packaging, and install from source
- docs/examples.md — copy‑paste examples
License
BSD‑3‑Clause. See LICENSE for details.
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。