OpenHands / OpenHands/extensions
Add Memanto MCP integration to catalog
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 148
- Forks
- 90
- Avg merge
- 1d 17h
- Merged PRs (30d)
- 36
Description
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):
- Package:
memanto-mcpviauvx(per docs above) - Required env:
MOORCHEH_API_KEY - Optional env:
MEMANTO_DEFAULT_AGENT_ID docsUrlin catalog: https://docs.memanto.ai/integrations/mcp
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
-
integrations/catalog/memanto.jsonvalidates againstintegrations/catalog.schema.json -
npm run build:integrationssucceeds -
getIntegrationCatalogEntry("memanto")(JS) /get_integration_catalog_entry_model("memanto")(Python) returns the entry with stdiouvx+memanto-mcpand env fields from the Memanto MCP docs - Memanto appears in MCP-filtered catalog listings (
listIntegrationCatalog({ mcp: true })/list_integration_catalog_models(mcp=True))
References
- Memanto MCP: https://docs.memanto.ai/integrations/mcp
- Memanto GitHub: https://github.com/moorcheh-ai/memanto
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review integrations/catalog.schema.json and nearby stdio API-key entries, then inspect the catalog lookup entry points named in the acceptance criteria. Add the Memanto catalog data from the linked MCP documentation and run npm run build:integrations. Done means the generated integrations/catalog-index.js builds and both JavaScript and Python catalog lookups include the entry in MCP-filtered results.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- javascript, python
- Domain
- api, tooling
- Issue type
- Feature
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Active
- Clarity
- Clearly specified
- Newbie friendliness
- 88/100