MCP server: persistent, self-revising hypothesis-DAG for agentic R&D
Connect Hypotree to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server: persistent, self-revising hypothesis-DAG for agentic R&D. The hypotree mcp server is what makes that connection.
A persistent, self-revising hypothesis DAG for agentic R&D — exposed as an MCP server.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
create_hypotheses — Create one or many nodes with parent_ids, exclusion_group, is_goalget_next_targets — Thompson Sampling — returns the next hypothesis to test, under a leaserecord_evidence — Record experiment results; triggers write-back propagationgenerate_learning_path — What we learned, in order, and what it cost — separates conclusions an experiment paid for from ones the engine inferred freeget_workspace_info — Which belief state you are connected to and which layer chose it — start here when the graph is unexpectedly emptyupdate_status — Manually set node status (rarely needed — the engine does it)get_dag_context — Get a subgraph view for the agent's context windowrender_dag_map — Mermaid.js diagram of the current belief stateget_goal_status — Check whether the goal node is metget_conflicts — List unresolved conflicts (integration failures)suggest_discriminating_experiment — For a conflict, suggest the swap that separates the culpritslist_nodes — List/filter nodes by status, depth, or exclusion groupInstallation goes through your MCP client rather than a global install: point it at hypotree on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: HYPOTREE_WORKSPACE_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Hypotree's toolset — create_hypotheses, get_next_targets, record_evidence and 11 more — is a fair guide to whether it matches your workflow.
This entry was verified against Hypotree's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| create_hypotheses | Create one or many nodes with parent_ids, exclusion_group, is_goal |
| get_next_targets | Thompson Sampling — returns the next hypothesis to test, under a lease |
| record_evidence | Record experiment results; triggers write-back propagation |
| generate_learning_path | What we learned, in order, and what it cost — separates conclusions an experiment paid for from ones the engine inferred free |
| get_workspace_info | Which belief state you are connected to and which layer chose it — start here when the graph is unexpectedly empty |
| update_status | Manually set node status (rarely needed — the engine does it) |
| get_dag_context | Get a subgraph view for the agent's context window |
| render_dag_map | Mermaid.js diagram of the current belief state |
| get_goal_status | Check whether the goal node is met |
| get_conflicts | List unresolved conflicts (integration failures) |
| suggest_discriminating_experiment | For a conflict, suggest the swap that separates the culprits |
| list_nodes | List/filter nodes by status, depth, or exclusion group |
| get_evidence_history | Full evidence trail for a node |
| get_active_claims | List nodes with active leases |
{
"mcpServers": {
"hypotree": {
"command": "uvx",
"args": ["hypotree"],
"env": {
"HYPOTREE_WORKSPACE_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| HYPOTREE_WORKSPACE_ID | Configuration value read at startup. | Optional |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.