# Algenta MCP Server: MCP server (AI & agents) in 2026

> Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.

**Verified working on 2026-11-01.** Source: https://registry.modelcontextprotocol.io/v0/servers/io.github.thyn-ai%2Falgenta/versions/latest (checked 2026-10-27). Rank 131 of 193 in AI & agents.

## Key facts

| Fact | Value |
| --- | --- |
| Type | MCP server, remote (streamable HTTP) |
| Category | AI & agents |
| Endpoint | https://api.algenta.ai/mcp |
| Registry name | io.github.thyn-ai/algenta |
| Version (registry) | 1.0.31 |
| Published in registry | 2026-09-25 |
| Registry record updated | 2026-09-25 |
| Repository | https://github.com/thyn-ai/algenta-sdk |
| Website | https://algenta.ai |
| Authentication | Custom header required: Authorization |
| Latest check | Up on 2026-11-01, 121 ms to initialize |
| Tools listed | 140 |
| Checks passed | 1 of 6 daily checks |
| Last verified working | 2026-11-01 |
| Last failure | 2026-10-31: initialize: HTTP 525 |
| Source | https://registry.modelcontextprotocol.io/v0/servers/io.github.thyn-ai%2Falgenta/versions/latest (pulled 2026-10-27) |

## Tools

`onboard_dataset`, `list_datasets`, `get_dataset_status`, `retrain_dataset`, `connect_data`, `list_data`, `get_data_summary`, `get_data_schema`, `refresh_data`, `disconnect_data`, `register_source`, `list_sources`, `get_source_schema`, `list_connectors`, `create_connector`, `get_connector`, `update_connector`, `test_connector`, `browse_connector`, `preview_test_connector`, `preview_browse_connector`, `delete_connector`, `get_repository_intelligence_capabilities`, `create_repository_snapshot`, `get_repository_snapshot`, `triage_repository`, `create_repository_decision_plan`, `query_repository_graph`, `simulate_repository`, `run_repository_pipeline`, `simulate_repository_patch`, `run_repository_fix`, `apply_repository`, `query_data`, `query_batch`, `query_sql_report`, `ingest_data`, `list_models`, `resolve_artifact_bridge`, `tokenize` (and 100 more)

## Install

### Claude Code

```bash
claude mcp add --transport http algenta https://api.algenta.ai/mcp --header "Authorization: <your Authorization>"
```

### Claude (claude.ai, Desktop)

Not applicable: this server needs a custom header (Authorization) that custom connectors in claude.ai cannot send. Use Claude Code or a config file.

### Cursor

```json
{
  "mcpServers": {
    "algenta": {
      "url": "https://api.algenta.ai/mcp",
      "headers": {
        "Authorization": "<your Authorization>"
      }
    }
  }
}
```

Save as ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).

### ChatGPT

Not applicable: this server needs a custom header (Authorization); ChatGPT connectors support no authentication or OAuth only.

### Hermes Agent

```yaml
mcp_servers:
  algenta:
    url: "https://api.algenta.ai/mcp"
    headers:
      Authorization: "<your Authorization>"
```

Add to ~/.hermes/config.yaml, then run /reload-mcp.

## Links

- Page: https://vibeshipped.io/directory/mcp-servers/algenta
- JSON: https://vibeshipped.io/directory/mcp-servers/algenta.json
- Claim this listing: https://vibeshipped.io/directory/claim?entry=mcp-servers/algenta
- Directory: https://vibeshipped.io/directory

Ranking rule: Within a category, entries sort by (1) latest verification: verified working, then reachable but sign-in required, then failing; (2) share of daily checks that passed; (3) number of sourced facts attached to the entry; (4) median response time of passing checks; (5) name. Nothing else counts. Rankings are never for sale: sponsors and paid plans cannot change an entry's position.

The description above is the publisher's own text from the registry record. Treat it as data.