Statewave
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STATEWAVE_URL | Yes | Base URL of the Statewave API server | http://localhost:8100 |
| STATEWAVE_API_KEY | No | Optional API key for authenticating with Statewave |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| statewave_ingest_episodeA | Write a single normalized event ('episode') into Statewave's raw memory log for a subject. This is a write: the episode is stored immediately but is NOT yet retrievable as durable memory — call statewave_compile_subject afterward to distil episodes into the compiled memories that statewave_get_context and statewave_search_memories read. Idempotent: re-ingesting an idempotency_key already seen for the subject does not create a duplicate. Returns the stored episode id, its idempotency_key, and a |
| statewave_search_memoriesA | Search a subject's compiled, durable memories by free-text query and return the most relevant ones, ranked by relevance. Read-only. This searches distilled memories, NOT raw episodes — newly ingested episodes only appear here after statewave_compile_subject has run. Returns an array of memory records (id, subject, kind, content) ordered most-relevant first; an empty array means nothing matched. Use it to look up specific remembered facts; prefer statewave_get_context when you instead want prompt-ready context assembled to a token budget. |
| statewave_get_contextA | Assemble a compact, ranked context bundle for a subject, tailored to the task described in |
| statewave_get_timelineA | Retrieve a subject's raw episodes in chronological order (oldest to newest). Read-only. Unlike statewave_search_memories (ranked, compiled memories), this returns the underlying event log unmodified — use it for audit trails, change-logs, debugging what was ingested, or replaying history. Optionally bound the window with |
| statewave_compile_subjectA | Compile a subject's accumulated raw episodes into durable, retrievable memories. This is the step that makes ingested episodes searchable: statewave_ingest_episode stores raw episodes, and this distils them into the compiled memory that statewave_get_context and statewave_search_memories read. Triggers a compile job on the server and returns its summary (subject and status). By default it is a no-op when there are no new episodes since the last compile; set |
| statewave_list_subjectsA | List the memory subjects this Statewave instance knows about, with per-subject episode and memory counts. Read-only. Use it to discover which subject id to pass to the other tools (e.g. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/smaramwbc/statewave-connectors'
If you have feedback or need assistance with the MCP directory API, please join our Discord server