Vendor-sourced facts on native integrations between SaaS tools, with sources and checked dates.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Reports whether two SaaS tools have a native integration. Tool names are matched loosely (slugs, product names, common abbreviations, small typos) and the matched slugs are returned. Tiers: "verified" = taken from vendor documentation, with source URLs and a checked date. "listed_unverified" = directory data lists the pair but no vendor source is recorded, so no details are returned. "unknown" = no data. Only a verified result with status "no_native" means the vendors confirm there is no native integration. A verified result includes the mechanism, the direction data moves, what syncs, plan requirements, source URLs and the date checked.
First tool: name or slug, for example "Salesforce" or "canvas-lms".
Second tool: name or slug, for example "Vanta".
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http integration-facts https://integratestack.com/mcp
Reports whether two SaaS tools have a native integration. Tool names are matched loosely (slugs, product names, common abbreviations, small typos) and the matched slugs are returned. Tiers: "verified" = taken from vendor documentation, with source URLs and a checked date. "listed_unverified" = directory data lists the pair but no vendor source is recorded, so no details are returned. "unknown" = no data. Only a verified result with status "no_native" means the vendors confirm there is no native integration. A verified result includes the mechanism, the direction data moves, what syncs, plan requirements, source URLs and the date checked.
| Argument | Type | Description |
|---|---|---|
| tool_a* | string | First tool: name or slug, for example "Salesforce" or "canvas-lms". |
| tool_b* | string | Second tool: name or slug, for example "Vanta". |
{
"type": "object",
"required": [
"tool_a",
"tool_b"
],
"properties": {
"tool_a": {
"type": "string",
"description": "First tool: name or slug, for example \"Salesforce\" or \"canvas-lms\"."
},
"tool_b": {
"type": "string",
"description": "Second tool: name or slug, for example \"Vanta\"."
}
},
"additionalProperties": false
}Lists what is known about one tool's native integrations, in two separate groups. "verified" rows come from vendor documentation and carry a status, mechanism, data direction and checked date. "listed_unverified" rows are tools that directory data lists as integrating, with no source and no details. A tool missing from both groups is unknown, which is not evidence that no integration exists.
| Argument | Type | Description |
|---|---|---|
| tool* | string | Tool name or slug, for example "Drata". |
{
"type": "object",
"required": [
"tool"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool name or slug, for example \"Drata\"."
}
},
"additionalProperties": false
}Resolves a product name or a category to tool slugs and hub page URLs. Use it to find the slug for a tool or to see which tools are covered in a category. Returns at most 25 results plus the full category list.
| Argument | Type | Description |
|---|---|---|
| query* | string | Name, partial name or keyword, for example "hub" or "CRM". Use an empty string to list a whole category. |
| category | string | Optional category filter, for example "CRM" or "Compliance". |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Name, partial name or keyword, for example \"hub\" or \"CRM\". Use an empty string to list a whole category."
},
"category": {
"type": "string",
"description": "Optional category filter, for example \"CRM\" or \"Compliance\"."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 12, 2026.