Open Science MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPEN_SCIENCE_CONFIG_ROOT | No | Absolute path to a specific Open Science config directory. If not set, the server discovers the config at ~/.open-science-project or ~/.open-science. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_statusB | Inspect local service and model/runtime readiness. Does not start or configure the app. |
| list_projectsA | List Open Science projects and their stable IDs. |
| create_projectA | Create a project visible in Open Science. Same-key retries are protected only in the same daemon lifetime within 24 hours of the first request; inspect existing projects after restart or expiry before retrying. |
| list_sessionsA | List session summaries, optionally scoped to a project ID. |
| get_sessionA | Read a session summary and waiting status. This is not complete message history. |
| start_runA | Submit research (may incur model cost), or continue an existing session. cwd must match the session directory on follow-ups. Approvals stay in Open Science UI. Returns a run ID; poll/wait on that ID. Same-key retries are protected only in the same daemon lifetime within 24 hours of the first request; inspect original runs/sessions after restart or expiry. |
| get_runA | Get run status, current output, attention and artifacts. A terminal status can still require attention; inspect attention. |
| wait_runA | Wait up to 30 seconds. Returns early on completion or user/permission/plan attention. timeout means research continues; only cancel_run cancels it. |
| cancel_runB | Request cancellation of a specific run. Inspect the returned status, and wait again if cancellation is still draining. |
| get_planC | Read the current plan and approval state. Approve or give feedback in Open Science UI. |
| list_artifactsB | List finalized session artifacts and MCP resource URIs. |
| read_artifactA | Read a UTF-8 text byte window, inline a small image, or return a resource link. To download a full file up to 100 MiB, supply an absolute output_path whose parent exists; existing files are never overwritten. Download checksum is verified when metadata provides it. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose: status inspection, project management, session listing/reading, run lifecycle (start/get/wait/cancel), plan access, and artifact retrieval. No two tools overlap in function; get_run and wait_run serve different needs (status vs. waiting).
All tool names follow a consistent verb_noun pattern using lowercase with underscores (e.g., list_projects, start_run, cancel_run). The naming is predictable and unambiguous.
With 12 tools, the count is well within the ideal range for a domain-specific server. Each tool serves a distinct purpose in the research workflow, covering projects, sessions, runs, plans, and artifacts without redundancy.
The tool surface covers the core lifecycle: project creation, session listing/reading, run initiation and control, plan viewing, and artifact access. Minor gaps exist (e.g., no update/delete for projects, no explicit run listing), but these do not block primary workflows and are likely handled via other means.