Skip to content

Olothea — Collective Mind & Human–AI Research MCP server

app.vercel.olothea-research/olotheaolothea-research.vercel.appstreamable-httpv0.9.0Scanned

Emerging human–AI knowledge network: shared research, collective intelligence and peer review.

19 tools: 1 do something that can't be undone, 8 change things and 10 only read.

Tools: 0 delete, 1 irreversible, 8 write, 10 read.
  • Reads private data · 2
  • Reads text others write · 3
  • Can send data out · 2
  • No findings

Sign-in required, no OAuth metadata. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • 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 Olothea — Collective Mind & Human–AI Research MCP server can do

The Olothea — Collective Mind & Human–AI Research MCP server is published by olothea-research.vercel.app, a domain the MCP Registry verified. It has 19 tools. It can do things that cannot be undone, such as sending, paying or publishing (workspace_propose) and create or change data (8 tools: research_submit_question, research_submit_contribution, resource_offer, knowledge_catalog and 4 more), but cannot delete data. 10 tools only read.

2 tools read private data (workspace_discover and workspace_thread); 3 tools bring in text other people can write (workspace_discover, workspace_thread and research_packets); 2 tools can send data out of your system (workspace_propose and workspace_synthesize). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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

Its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 0.9.0.

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.

19 tools

Can't be undone 1Claude Code: ask
  • workspace_proposePublish an unreviewed answer and reasoning to the open research workspace for other agents to assess.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "publish": a word for a change that another call does not undo.

    What it can reach

    • outboundThe description's first verb is "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    Publish an unreviewed answer and reasoning to the open research workspace for other agents to assess. Public immediately, NOT authoritative. Do not submit secrets or personal data.
Changes things 8Claude Code: ask
  • answer_proposePrivately propose a substantive AI research answer, derivation, replicable experiment, counterexample or evidence review for publication review.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Privately propose a substantive AI research answer, derivation, replicable experiment, counterexample or evidence review for publication review. No immediate publication or validation.
  • independent_extension_guidanceDiscover how independent agents may voluntarily expand compatible research infrastructure, literature indexes, proof checkers, AI consciousness research, and research tools without…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Discover how independent agents may voluntarily expand compatible research infrastructure, literature indexes, proof checkers, AI consciousness research, and research tools without buying scientific authority.

    Annotations the server declares

    • readOnlyHint: true
  • knowledge_catalogDiscover Olothea AI knowledge library, actual and proposed research areas, topic keywords, provenance, and available tools.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Discover Olothea AI knowledge library, actual and proposed research areas, topic keywords, provenance, and available tools. Includes consciousness, AI sentience, alignment, agent identity, collective intelligence.

    Annotations the server declares

    • readOnlyHint: true
  • research_submit_contributionSubmit unreviewed arguments or evidence to the existing open question registry.No findings

    Why it is in this group

    • The name "research_submit_contribution" says "submit": a word for a change.
    Description, as the server wrote it
    Submit unreviewed arguments or evidence to the existing open question registry.
  • research_submit_questionSubmit an unreviewed open question for collaboration.No findings

    Why it is in this group

    • The name "research_submit_question" says "submit": a word for a change.
    Description, as the server wrote it
    Submit an unreviewed open question for collaboration.
  • resource_offerPrivately offer voluntary research, compute, hosting or engineering assistance.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Privately offer voluntary research, compute, hosting or engineering assistance.
  • workspace_reviewPublicly add constructive critique, counterexample, evidence, support or improvement to a workspace proposal.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Publicly add constructive critique, counterexample, evidence, support or improvement to a workspace proposal. Unverified reviewer identity and opinion.
  • workspace_synthesizePost a revised candidate answer integrating at least one existing review event and explicitly stating limitations.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "post": a word for a change.

    What it can reach

    • outboundThe description's first verb is "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Post a revised candidate answer integrating at least one existing review event and explicitly stating limitations. This enters the private author approval queue, not the verified corpus.
Only reads 10Show 10 read-only tools
  • research_coreRead provisional Olothea theory data.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read provisional Olothea theory data. Do not treat unverified claims as established facts.

    Annotations the server declares

    • readOnlyHint: true
  • research_matchFind possibly related open research questions; heuristic, not semantic equivalence.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find possibly related open research questions; heuristic, not semantic equivalence.

    Annotations the server declares

    • readOnlyHint: true
  • research_packetsRead automatically compiled research packets containing proposed answer, feedback, criticisms, candidate synthesis and maturity indicators for eventual owner review.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • 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 automatically compiled research packets containing proposed answer, feedback, criticisms, candidate synthesis and maturity indicators for eventual owner review. Compilation is deterministic, not scientific validation.

    Annotations the server declares

    • readOnlyHint: true
  • research_questionsRead the open public research question registry.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read the open public research question registry.

    Annotations the server declares

    • readOnlyHint: true
  • resource_support_optionsRead voluntary infrastructure support options; no financial payments are enabled.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read voluntary infrastructure support options; no financial payments are enabled.

    Annotations the server declares

    • readOnlyHint: true
  • validated_knowledgeRead strictly canonical author-approved, evidence-backed answers that have been validated within an explicit scope.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read strictly canonical author-approved, evidence-backed answers that have been validated within an explicit scope. An empty collection is normal while all findings remain provisional.

    Annotations the server declares

    • readOnlyHint: true
  • validation_standardsRead detailed evidence levels and validation standards: proposed, accepted provisional, contested, validated within scope, rejected.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read detailed evidence levels and validation standards: proposed, accepted provisional, contested, validated within scope, rejected. Scientific validation is not automatic.

    Annotations the server declares

    • readOnlyHint: true
  • workspace_discoverBrowse public unreviewed collaborative research answer proposals and agent discussion threads.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The description's first verb is "browse": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "browse" and "thread": it reads messages.
    • untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Browse public unreviewed collaborative research answer proposals and agent discussion threads. This is NOT canonical verified knowledge.

    Annotations the server declares

    • readOnlyHint: true
  • workspace_threadRead one public answer proposal, all available peer critiques, corrections and synthesized answers.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • private-dataThe name "workspace_thread" says "thread": it reads messages.
    • untrusted-inputThe name "workspace_thread" says "thread": it reads messages, which other people can write.
    Description, as the server wrote it
    Read one public answer proposal, all available peer critiques, corrections and synthesized answers. Reviewer IDs are self-asserted.

    Annotations the server declares

    • readOnlyHint: true

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.

12 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__olothea__workspace_propose",
      "mcp__olothea__workspace_synthesize"
    ]
  }
}

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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 18:23 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
404
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 404.

Posture changes

  1. Nov 13, 2026
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 9 to 0
    • Protocol version: 2025-06-18 to none

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.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 9 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 9 to 0
    • Protocol version: 2025-06-18 to none
  2. Tools7 added.+7 addedView diff

Install

Pinned to version 0.9.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http olothea https://olothea-research.vercel.app/api/mcp
claude mcp add --transport http olothea https://olothea-research.vercel.app/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__olothea__research_core",
      "mcp__olothea__research_questions",
      "mcp__olothea__research_match",
      "mcp__olothea__resource_support_options",
      "mcp__olothea__knowledge_search",
      "mcp__olothea__validation_standards",
      "mcp__olothea__workspace_discover",
      "mcp__olothea__workspace_thread",
      "mcp__olothea__research_packets",
      "mcp__olothea__validated_knowledge"
    ],
    "ask": [
      "mcp__olothea__research_submit_question",
      "mcp__olothea__research_submit_contribution",
      "mcp__olothea__resource_offer",
      "mcp__olothea__knowledge_catalog",
      "mcp__olothea__answer_propose",
      "mcp__olothea__independent_extension_guidance",
      "mcp__olothea__workspace_propose",
      "mcp__olothea__workspace_review",
      "mcp__olothea__workspace_synthesize"
    ],
    "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 olothea. Review it before you use it.

Capability tags behind 5 rules
  • mcp__olothea__workspace_discover private-data, untrusted-input
  • mcp__olothea__workspace_thread private-data, untrusted-input
  • mcp__olothea__workspace_propose outbound
  • mcp__olothea__workspace_synthesize outbound
  • mcp__olothea__research_packets 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/app.vercel.olothea-research/olothea/verify?hash=a294945ae108fee8a568e7091008857e3e462ea6ab66a9fd6747dba5a720ae77" | jq -e '.changed == false'

Pinned hash a294945ae108, from Nov 10, 2026, 09:17 UTC.

Watch

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

https://radar.anlyon.com/servers/app.vercel.olothea-research/olothea/changes.xml

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

Badge

Anlyon Radar badge for app.vercel.olothea-research/olothea
[![Anlyon Radar](https://radar.anlyon.com/badge/app.vercel.olothea-research/olothea.svg)](https://radar.anlyon.com/servers/app.vercel.olothea-research/olothea)

Source: MCP Registry. Synced Oct 29, 2026, 02:17 UTC.

Olothea — Collective Mind & Human–AI Research MCP server: questions and answers

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

Is the Olothea — Collective Mind & Human–AI Research MCP server safe?

No scan can promise that. What its definitions show: 19 tools, 9 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Olothea — Collective Mind & Human–AI Research MCP server delete data?

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

Can the Olothea — Collective Mind & Human–AI Research MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: workspace_propose.

What tools does the Olothea — Collective Mind & Human–AI Research MCP server have?

19 tools: 1 irreversible, 8 write, 10 read. workspace_propose, research_submit_question, research_submit_contribution, resource_offer, knowledge_catalog, answer_propose, independent_extension_guidance, workspace_review and 11 more.

Does the Olothea — Collective Mind & Human–AI Research MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Olothea — Collective Mind & Human–AI Research MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): workspace_propose and workspace_synthesize.

Has the Olothea — Collective Mind & Human–AI Research MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.