Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
This system programmatically collects all Salesforce documentation from developer.salesforce.com (129 domains, 35,000+ pages), processes it into structured, curated knowledge files, and serves them to LLM agents via:
Salesforce documentation knowledge system — MCP server + Knowledge Graph for AI agents
_index.mdNo embeddings. No vector stores. No blind chunking.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"sf-docs": {
"command": "npx",
"args": ["-y", "-p", "@sfdxy/sf-documentation-knowledge", "sf-docs-mcp"],
"env": {
"SF_ACTIVE_DOMAINS": "apex-guide,apex-reference,lwc"
}
}
}
}
Remove the
envblock to search all 129 domains. See Domain Restriction for details.
Restart Claude Desktop.
Add to .vscode/mcp.json in your workspace (or globally in VS Code settings):
{
"servers": {
"sf-docs": {
"command": "npx",
"args": ["-y", "-p", "@sfdxy/sf-documentation-knowledge", "sf-docs-mcp"],
"env": {
"SF_ACTIVE_DOMAINS": "apex-guide,apex-reference,lwc"
}
}
}
}
Then use @sf-docs in Copilot Chat to query Salesforce documentation.
Add to your MCP config (~/.gemini/settings.json or project .gemini/settings.json):
{
"mcpServers": {
"sf-docs": {
"command": "npx",
"args": ["-y", "-p", "@sfdxy/sf-documentation-knowledge", "sf-docs-mcp"],
"env": {
"SF_ACTIVE_DOMAINS": "apex-guide,apex-reference,lwc"
}
}
}
}
Add in Settings -> MCP Servers -> Add Server:
sf-docsnpx -y -p @sfdxy/sf-documentation-knowledge sf-docs-mcpstdioSF_ACTIVE_DOMAINS=apex-guide,apex-reference,lwcAdd to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"sf-docs": {
"command": "npx",
"args": ["-y", "-p", "@sfdxy/sf-documentation-knowledge", "sf-docs-mcp"],
"env": {
"SF_ACTIVE_DOMAINS": "apex-guide,apex-reference,lwc"
}
}
}
}
Add to your OpenCode config (~/.config/opencode/config.json or project .opencode/config.json):
{
"mcpServers": {
"sf-docs": {
"command": "npx",
"args": ["-y", "-p", "@sfdxy/sf-documentation-knowledge", "sf-docs-mcp"],
"env": {
"SF_ACTIVE_DOMAINS": "apex-guide,apex-reference,lwc"
}
}
}
}
Point your MCP client to:
npx -y -p @sfdxy/sf-documentation-knowledge sf-docs-mcp
The server uses stdio transport and is compatible with any MCP client.
Why
-p+sf-docs-mcp?
The package ships two binaries:sf-knowledge(the data pipeline CLI) andsf-docs-mcp(the MCP server). Using-pinstalls the package and then explicitly calls thesf-docs-mcpbinary, ensuring you get the MCP server and not the CLI.
git clone https://github.com/Avinava/sf-documentation-knowledge.git
cd sf-documentation-knowledge
npm install
npm run build
npm run mcp:start
The MCP server loads the full 53k-node knowledge graph and 18,000+ code snippets into memory on startup (~5s) and serves all queries instantly.
Run directly from source:
npm run mcp:start
Or via npx (no clone required):
npx -y -p @sfdxy/sf-documentation-knowledge sf-docs-mcp
Agents can read these without making a tool call:
When working on a specific Salesforce product area (e.g., Revenue Cloud, Apex development), you can restrict all tools to only search within relevant domains. This reduces noise and improves result quality.
SF_ACTIVE_DOMAINS as a comma-separated list of domain IDs in your MCP client configsf_set_active_domains to change the active domains without restarting# Let the AI suggest domains for your task
sf_suggest_domains("building LWC components with Apex backend")
→ Suggests: lwc, apex-guide, apex-reference, lightning
# Set the suggested domains
sf_set_active_domains(domains: ["lwc", "apex-guide", "apex-reference", "lightning"])
# Check current state
sf_set_active_domains()
# Clear restrictions
sf_set_active_domains(clear: true)
See docs/domains.md for the full list organized by service category, or use sf_list_domains at runtime.
The repository comes pre-loaded with 35,000+ curated markdown files and a Knowledge Graph (53,000+ nodes, 450,000+ edges) covering 129 domains of Salesforce documentation.
Point your AI agent to the _index.md file in any domain folder. The index acts as a routing table telling the AI which files contain which topics:
knowledge/current/<domain-name>/_index.md
Each domain folder also has a SKILL.md in skills/<domain-name>/SKILL.md that teaches AI agents how to navigate the knowledge.
The graph at knowledge/current/graph.json connects all documentation with semantic relationships:
Inspect it with:
npm run graph:stats
See Graph Schema Documentation for the full schema with node/edge types, ID conventions, and a visual diagram.
To update the knowledge base with the latest Salesforce releases, run the pipeline in order:
npm run discover
Lists all documentation deliverables available from the Salesforce Index API (~127 deliverables).
# Collect a specific domain
npm run collect -- --domain cli-commands
# Collect all configured (P0) domains
npm run collect
# Collect ALL deliverables from the SF index API (121 domains, ~31k pages)
npm run collect -- --discover
# Process a specific domain
npm run process -- --domain cli-commands
# Process ALL collected domains
npm run process -- --discover
Automatically cleans HTML, strips noise, parses tables, formats code blocks, creates clean Markdown, and redacts any Salesforce tokens or secrets.
# Generate ALL collected domains and rebuild the full Knowledge Graph
npm run generate -- --discover
Builds the knowledge graph (cross-references, namespaces, service categories, doctype clustering), generates context files, and updates inventory docs.
npm run graph:stats
npm run collect -- --discover && npm run process -- --discover && npm run generate -- --discover
All pipeline commands support --domain <name> for single-domain processing and --discover for all-domain processing.
MIT © Avinava
129 domains | 35,438 knowledge files
Salesforce documentation knowledge system — MCP server + Knowledge Graph for AI agents
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Sf Documentation Knowledge ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 Salesforce documentation knowledge system — MCP server + Knowledge Graph for AI agents
