Skip to content

executable-science MCP server

science.executable/executable-scienceexecutable.sciencestreamable-httpv0.2.0Scanned

Read-only research pilot catalogue: task templates, resources, starter studies, capability status.

15 tools: 15 only read.

Tools: 0 delete, 0 irreversible, 0 write, 15 read.
  • Reads private data · 0
  • Reads text others write · 5
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the executable-science MCP server can do

The executable-science MCP server is published by executable.science, a domain the MCP Registry verified. It has 15 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

5 tools bring in text other people can write (get_public_review_index, get_public_review_item_bytes, list_public_review_coverage_page and 2 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 0.2.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Only reads 15Show 15 read-only tools
  • get_public_preprintRead one exact, completed public preprint disclosure.No findings

    Why it is in this group

    • The name "get_public_preprint" says "get": a word for reading.
    Description, as the server wrote it
    Read one exact, completed public preprint disclosure. A preprint is separate from journal acceptance; DOI registration, preservation and scientific verification are not inferred.
  • get_public_review_indexRead the index and exact section counts of one frozen, published review disclosure.Reads text others writeNo findings

    Why it is in this group

    • The name "get_public_review_index" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe name "get_public_review_index" says "get" and "review": it reads comments, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Read the index and exact section counts of one frozen, published review disclosure. Review, DOI, preservation and publication have separate states.
  • get_public_review_item_bytesRead at most 32 KiB of one exact frozen public-review item, including a section or child item too large for a page.Reads text others writeNo findings

    Why it is in this group

    • The name "get_public_review_item_bytes" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe name "get_public_review_item_bytes" says "get" and "review": it reads comments, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    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.
  • get_resourceRead one catalogued public resource by its identifier, including its recorded rights and provenance.No findings

    Why it is in this group

    • The name "get_resource" says "get": a word for reading.
    Description, as the server wrote it
    Read one catalogued public resource by its identifier, including its recorded rights and provenance.
  • get_starter_sourceDownload one original licensed starter ZIP as base64 with its SHA-256 and rights.No findings

    Why it is in this group

    • The name "get_starter_source" says "get": a word for reading.
    Description, as the server wrote it
    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.
  • get_starter_studyRead one licensed starter study's frozen inputs, archive digest, environment, expected interpretation and unrun status.No findings

    Why it is in this group

    • The name "get_starter_study" says "get": a word for reading.
    Description, as the server wrote it
    Read one licensed starter study's frozen inputs, archive digest, environment, expected interpretation and unrun status.
  • get_task_templateRead one frozen task template in full: its question, inputs, assumptions, comparison basis, stated limitations and revision digest.No findings

    Why it is in this group

    • The name "get_task_template" says "get": a word for reading.
    Description, as the server wrote it
    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.
  • list_public_review_coverage_pageRead one bounded page of a published review's frozen literature-coverage declarations.Reads text others writeNo findings

    Why it is in this group

    • The name "list_public_review_coverage_page" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe name "list_public_review_coverage_page" says "list" and "review": it reads comments, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Read one bounded page of a published review's frozen literature-coverage declarations. A declaration is not independent evidence of every cited passage.
  • list_public_review_finding_events_pageRead one bounded page of a published finding's frozen public events.Reads text others writeNo findings

    Why it is in this group

    • The name "list_public_review_finding_events_page" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe name "list_public_review_finding_events_page" says "list" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Read one bounded page of a published finding's frozen public events. Private or later responses are not included.
  • list_public_review_section_pageRead one bounded section of a frozen published review disclosure.Reads text others writeNo findings

    Why it is in this group

    • The name "list_public_review_section_page" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe name "list_public_review_section_page" says "list" and "review": it reads comments, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    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.
  • list_starter_studiesList original downloadable source studies with explicit licenses, archive digests, pinned catalog environments and unrun evidence status.No findings

    Why it is in this group

    • The name "list_starter_studies" says "list": a word for reading.
    Description, as the server wrote it
    List original downloadable source studies with explicit licenses, archive digests, pinned catalog environments and unrun evidence status.
  • list_task_templatesList the bounded, frozen questions this platform publishes for attempt.No findings

    Why it is in this group

    • The name "list_task_templates" says "list": a word for reading.
    Description, as the server wrote it
    List the bounded, frozen questions this platform publishes for attempt. Each carries a revision digest and its own stated limitations.
  • platform_statusReport the current stage and, for every capability, whether it is available and the stated reason.No findings

    Why it is in this group

    • The name "platform_status" says "status": a word for reading.
    Description, as the server wrote it
    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.
  • search_public_preprintsSearch only completed, currently accessible public preprint snapshots.No findings

    Why it is in this group

    • The name "search_public_preprints" says "search": a word for reading.
    Description, as the server wrote it
    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.
  • search_resourcesSearch public dataset, software, article, method and experiment listing metadata by title, summary, question, comparison, use case, source identity, rights and limits.No findings

    Why it is in this group

    • The name "search_resources" says "search": a word for reading.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write5
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:18 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http executable-science https://executable.science/api/mcp
claude mcp add --transport http executable-science https://executable.science/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__executable-science__get_public_preprint",
      "mcp__executable-science__get_public_review_index",
      "mcp__executable-science__get_public_review_item_bytes",
      "mcp__executable-science__get_resource",
      "mcp__executable-science__get_starter_source",
      "mcp__executable-science__get_starter_study",
      "mcp__executable-science__get_task_template",
      "mcp__executable-science__list_public_review_coverage_page",
      "mcp__executable-science__list_public_review_finding_events_page",
      "mcp__executable-science__list_public_review_section_page",
      "mcp__executable-science__list_starter_studies",
      "mcp__executable-science__list_task_templates",
      "mcp__executable-science__platform_status",
      "mcp__executable-science__search_public_preprints",
      "mcp__executable-science__search_resources"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as executable-science. Review it before you use it.

Capability tags behind 5 rules
  • mcp__executable-science__get_public_review_index untrusted-input
  • mcp__executable-science__get_public_review_item_bytes untrusted-input
  • mcp__executable-science__list_public_review_coverage_page untrusted-input
  • mcp__executable-science__list_public_review_finding_events_page untrusted-input
  • mcp__executable-science__list_public_review_section_page untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/science.executable/executable-science/verify?hash=0899161a9db1c683b239985adb72de94952dcc4664dd381f0f6a51640afe69e4" | jq -e '.changed == false'

Pinned hash 0899161a9db1, from Nov 19, 2026, 03:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/science.executable/executable-science/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for science.executable/executable-science
[![Anlyon Radar](https://radar.anlyon.com/badge/science.executable/executable-science.svg)](https://radar.anlyon.com/servers/science.executable/executable-science)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

executable-science MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the executable-science MCP server safe?

No scan can promise that. What its definitions show: 15 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the executable-science MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the executable-science MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the executable-science MCP server have?

15 tools: 15 read. get_public_preprint, get_public_review_index, get_public_review_item_bytes, get_resource, get_starter_source, get_starter_study, get_task_template, list_public_review_coverage_page and 7 more.

Does the executable-science MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the executable-science MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the executable-science MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.