Problem or Use Case
Memanto provides persistent semantic memory for agents over MCP (remember, recall, answer, etc.), but it is not listed in OpenHands/extensions, so Agent Canvas cannot show an install card on /mcp like Tavily or Kagi.
Official MCP documentation (source of truth for server name, env vars, and tools):
https://docs.memanto.ai/integrations/mcp
Desired Behavior
Add a catalog entry aligned with other stdio API-key MCP integrations (e.g. Tavily, Kagi):
Regenerate integrations/catalog-index.js with npm run build:integrations.
This is an opt-in MCP backend; it does not replace OpenHands built-in file memory.
Acceptance Criteria
References
Problem or Use Case
Memanto provides persistent semantic memory for agents over MCP (
remember,recall,answer, etc.), but it is not listed inOpenHands/extensions, so Agent Canvas cannot show an install card on/mcplike Tavily or Kagi.Official MCP documentation (source of truth for server name, env vars, and tools):
https://docs.memanto.ai/integrations/mcp
Desired Behavior
Add a catalog entry aligned with other stdio API-key MCP integrations (e.g. Tavily, Kagi):
memanto-mcpviauvx(per docs above)MOORCHEH_API_KEYMEMANTO_DEFAULT_AGENT_IDdocsUrlin catalog: https://docs.memanto.ai/integrations/mcpRegenerate
integrations/catalog-index.jswithnpm run build:integrations.This is an opt-in MCP backend; it does not replace OpenHands built-in file memory.
Acceptance Criteria
integrations/catalog/memanto.jsonvalidates againstintegrations/catalog.schema.jsonnpm run build:integrationssucceedsgetIntegrationCatalogEntry("memanto")(JS) /get_integration_catalog_entry_model("memanto")(Python) returns the entry with stdiouvx+memanto-mcpand env fields from the Memanto MCP docslistIntegrationCatalog({ mcp: true })/list_integration_catalog_models(mcp=True))References