executable-science
Read-only research pilot catalogue: task templates, resources, starter studies, capability status.
Should I use this
Quality & Safety
Findings (6)
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains suspicious base64-like encoded stringin get_public_review_item_bytes
- LOWTool 'platform_status' description lacks action verbin platform_status
- LOWTool 'list_public_review_coverage_page' name length outside 3-30 rangein list_public_review_coverage_page
- LOWTool 'list_public_review_finding_events_page' name length outside 3-30 rangein list_public_review_finding_events_page
- LOWTool 'list_public_review_section_page' name length outside 3-30 rangein list_public_review_section_page
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"executable-science": {
"url": "https://executable.science/api/mcp"
}
}
}Remote endpoints
https://executable.science/api/mcpstreamable-httpWhat it can do
Tool inventory
Tools (15)
🟢get_public_preprint(version_id)
Read one exact, completed public preprint disclosure. A preprint is separate from journal acceptance; DOI registration, preservation and scientific verification are not inferred.
Input Schema
{
"type": "object",
"properties": {
"version_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
}
},
"required": [
"version_id"
],
"additionalProperties": false
}🟢get_public_review_index(disclosure_id)
Read the index and exact section counts of one frozen, published review disclosure. Review, DOI, preservation and publication have separate states.
Input Schema
{
"type": "object",
"properties": {
"disclosure_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
}
},
"required": [
"disclosure_id"
],
"additionalProperties": false
}🟢get_public_review_item_bytes(disclosure_id, section, ordinal, parent_id, offset, ...)
Read at most 32 KiB of one exact frozen public-review item, including a section or child item too large for a page. Follow next_action, match disclosure/version/section/parent/ordinal/item identity and digest across chunks, then verify SHA-256 of the assembled canonical JSON bytes before parsing. This is read-only and grants no publication or verification authority.
Input Schema
{
"type": "object",
"properties": {
"disclosure_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
},
"section": {
"type": "string",
"enum": [
"supplied_authors",
"reviews",
"findings",
"editorial_decisions",
"limitations",
"finding_events",
"review_coverage"
]
},
"ordinal": {
"type": "integer",
"minimum": 0,
"maximum": 20500
},
"parent_id": {
"type": "string",
"minLength": 1,
"maxLength": 100
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 32768,
"default": 32768
},
"expected_payload_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"required": [
"disclosure_id",
"section",
"ordinal"
],
"additionalProperties": false
}🟢get_resource(resource_id)
Read one catalogued public resource by its identifier, including its recorded rights and provenance.
Input Schema
{
"type": "object",
"properties": {
"resource_id": {
"type": "string",
"description": "Catalogue identifier."
}
},
"required": [
"resource_id"
],
"additionalProperties": false
}🟢get_starter_source(study_id)
Download one original licensed starter ZIP as base64 with its SHA-256 and rights. Source has not run or been verified; submitting it still requires isolated ingestion.
Input Schema
{
"type": "object",
"properties": {
"study_id": {
"type": "string"
}
},
"required": [
"study_id"
],
"additionalProperties": false
}🟢get_starter_study(study_id)
Read one licensed starter study's frozen inputs, archive digest, environment, expected interpretation and unrun status.
Input Schema
{
"type": "object",
"properties": {
"study_id": {
"type": "string"
}
},
"required": [
"study_id"
],
"additionalProperties": false
}🟢get_task_template(task_id)
Read one frozen task template in full: its question, inputs, assumptions, comparison basis, stated limitations and revision digest. The digest pins the exact revision an attempt was prepared against.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task template identifier."
}
},
"required": [
"task_id"
],
"additionalProperties": false
}🟢list_public_review_coverage_page(disclosure_id, cursor, limit, review_id)
Read one bounded page of a published review's frozen literature-coverage declarations. A declaration is not independent evidence of every cited passage.
Input Schema
{
"type": "object",
"properties": {
"disclosure_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
},
"cursor": {
"type": "integer",
"minimum": 0,
"default": 0
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"review_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
}
},
"required": [
"disclosure_id",
"review_id"
],
"additionalProperties": false
}🟢list_public_review_finding_events_page(disclosure_id, cursor, limit, finding_id)
Read one bounded page of a published finding's frozen public events. Private or later responses are not included.
Input Schema
{
"type": "object",
"properties": {
"disclosure_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
},
"cursor": {
"type": "integer",
"minimum": 0,
"default": 0
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"finding_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
}
},
"required": [
"disclosure_id",
"finding_id"
],
"additionalProperties": false
}🟢list_public_review_section_page(disclosure_id, cursor, limit, section)
Read one bounded section of a frozen published review disclosure. Finding events and literature coverage have separate child pages; follow next_action for complete history.
Input Schema
{
"type": "object",
"properties": {
"disclosure_id": {
"type": "string",
"pattern": "^[a-f0-9]{32}$"
},
"cursor": {
"type": "integer",
"minimum": 0,
"default": 0
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"section": {
"type": "string",
"enum": [
"supplied_authors",
"reviews",
"findings",
"editorial_decisions",
"limitations"
]
}
},
"required": [
"disclosure_id",
"section"
],
"additionalProperties": false
}🟢list_starter_studies
List original downloadable source studies with explicit licenses, archive digests, pinned catalog environments and unrun evidence status.
Input Schema
{
"type": "object",
"additionalProperties": false
}🟢list_task_templates
List the bounded, frozen questions this platform publishes for attempt. Each carries a revision digest and its own stated limitations.
Input Schema
{
"type": "object",
"additionalProperties": false
}⚪platform_status
Report the current stage and, for every capability, whether it is available and the stated reason. Several capabilities are gated; this tool is the authoritative answer on which.
Input Schema
{
"type": "object",
"additionalProperties": false
}🟢search_public_preprints(query, cursor, limit)
Search only completed, currently accessible public preprint snapshots. Each result names an exact version and remains separate from journal articles, DOI registration, preservation and scientific verification.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 300
},
"cursor": {
"type": "string",
"pattern": "^[1-9][0-9]{0,11}:[a-f0-9]{32}$"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
}
},
"additionalProperties": false
}🟢search_resources(query, kind, collection, rights, page, ...)
Search public dataset, software, article, method and experiment listing metadata by title, summary, question, comparison, use case, source identity, rights and limits. Results retain source revision and readiness; they are not scientific evidence.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 300,
"description": "Words matched across public listing metadata."
},
"kind": {
"type": "string",
"enum": [
"dataset",
"software_package",
"published_article",
"method_reference",
"original_experiment"
]
},
"collection": {
"type": "string",
"description": "Exact public collection ID."
},
"rights": {
"type": "string",
"enum": [
"evidence_recorded",
"needs_review"
]
},
"page": {
"type": "integer",
"minimum": 1,
"maximum": 10000,
"default": 1
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
}
},
"additionalProperties": false
}Community
Evidence