Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Darwin

REMOTE · MCP.DARWIN.SO

Browse the agentic web with Darwin: search, communicate, authenticate, and act through agents.

Available components

−14 this week 67 Trust /100

Last scanned (20 hours ago)

Scores higher than 52% of remote servers

Unreachable for 1 day in a row. Last reached 20 Nov 2026.

Category AI and Machine Learning

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
  • Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
  • Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified

Unverified: 5 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

What we tested

Checks we ran (4)

  • TLS certificate
  • HTTPS
  • DNSSEC
  • Transport

Checks we could not complete (7)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  • HSTS header in Endpoint SecurityHSTS not yet verified: we couldn't read the response headers to check for it.
  • Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
  • Tool coverage in Tool Coverage (scores 0 for this)Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
  • Tool safety in Tool Safety (scores 0 for this)Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
  • Capabilities in Capabilities (scores 0 for this)Capabilities not yet verified: we couldn't read the endpoint's capabilities.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • Stability: fail → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • HSTS header: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
    • Schema quality: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
  • 20 Nov 26 +3
    • Schema quality: fail → pass ▲ functional
  • 19 Nov 26 −17
    • Authorization: pass → unverified ▼ security
    • Schema quality: pass → fail ▼ functional
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 18 Nov 26 +46
    • Stability: unverified → fail ▼ security
    • A breaking change shipped without a version bump: still 0.13.1 ▼ security
    • Tool “orchestrate” was removed ▼ security
    • Tool “publish” was removed ▼ security
    • Authorization: unverified → pass ▲ security
    • Injection markers: unverified → pass ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “build” rewrote its description, which is the text the model reads security
    • Tool “navigate” rewrote its description, which is the text the model reads security
    • Tool “run” rewrote its description, which is the text the model reads security
    • Tool coverage: 65% → 58% ▼ functional
    • Endpoint reachability: behind authorisation → reachable ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Schema quality: unverified → 100 ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • Schema quality: fail → pass ▲ functional
    • “live-search” reworded the description of “mode” cosmetic
  • 17 Nov 26 −46
    • Endpoint reachability: unreachable → behind authorisation ▼ security
    • HSTS header: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
    • Tool safety: Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools. security
    • Tool coverage: Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools. functional
    • Schema quality: Schema blocked by authentication: the endpoint requires auth we don't have to read it. functional
    • Capabilities: Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. functional
  • 15 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • Stability: fail → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Authorization: pass → unverified ▼ security
    • HSTS header: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Schema quality: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
  • 12 Nov 26 +46
    • Stability: unverified → fail ▼ security
    • Authorization: unverified → pass ▲ security
    • Injection markers: unverified → pass ▲ security
    • Endpoint reachability: behind authorisation → reachable ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Schema quality: unverified → 100 ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • Server version: 0.13.0 → 0.13.1 functional
  • 11 Nov 26 −47
    • Endpoint reachability: unreachable → behind authorisation ▼ security
    • Transport: unverified → pass ▲ security
    • HSTS header: unverified → pass ▲ security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
    • Tool safety: Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools. security
    • Tool coverage: Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools. functional
    • Schema quality: Schema blocked by authentication: the endpoint requires auth we don't have to read it. functional
    • Capabilities: Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.darwin.so/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.darwin.so CN=Cloudflare TLS Issuing ECC CA 3,O=SSL Corporation,C=US 5 Nov 2026 3 Feb 2027 ECDSA 256 ECDSA-SHA256 5e21f83ba8d64f0bd63a3dca16848379
SANs: mcp.darwin.so
CN=Cloudflare TLS Issuing ECC CA 3,O=SSL Corporation,C=US (CA) CN=SSL.com TLS Transit ECC CA R2,O=SSL Corporation,C=US 29 May 2025 27 May 2035 ECDSA 256 ECDSA-SHA384 31eee88afb87cd9ef8336604743f9b27
CN=SSL.com TLS Transit ECC CA R2,O=SSL Corporation,C=US (CA) CN=SSL.com TLS ECC Root CA 2022,O=SSL Corporation,C=US 21 Oct 2022 17 Oct 2037 ECDSA 384 ECDSA-SHA384 604d8af8d00ba8748b955853172c5f2e
CN=SSL.com TLS ECC Root CA 2022,O=SSL Corporation,C=US (CA) CN=AAA Certificate Services,O=Comodo CA Limited,L=Salford,ST=Greater Manchester,C=GB 1 Aug 2025 31 Dec 2028 ECDSA 384 SHA256-RSA 173dca60ea9f8e1026dafcd72810e48e

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.darwin.so. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
so. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Inconclusive

We could not reach the endpoint well enough to judge its authorisation posture.

Result Inconclusive

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.darwin.so/mcp Unreachable
http (plaintext) http://mcp.darwin.so/mcp HTTPS enforced 301 https://mcp.darwin.so/mcp
MCP tools · 9 exposed · ~948 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
build ~49

Author, test, and prepare publication of private revisioned agent drafts. Read actions require builder:read; mutations require builder:write.

NameTypeReqDescription
command–yes–
idempotencyKeystringyes–

Structured output declared, but exposes no named fields.

No examples provided.

get_account ~61

Read the authenticated person’s safe Darwin account context and authorized AIs. Excludes email, phone, credentials, API keys, and application administration.

NameTypeReqDescription
aiIdstring–Optional authorized AI context to select in the response; omit to use the active selection.
NameTypeReqDescription
accountobjectyes–
activeAi–yes–
aisarrayyes–

No examples provided.

get_thread ~61

Read an owned Navigate or agent thread using threadId. Pass the issued continuation token for a guest Navigate thread. Agent guest credentials remain in host custody. Use the returned pagination cursor for earlier messages. Reading never starts work or grants approval. Legacy thread arguments remain accepted.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

live-search ~349

Send an explicit live-search turn. Omit threadId to start a thread; supply the returned threadId to continue. Use a stable clientMessageId for retries. This tool never automatically reclassifies the chosen mode. Execution and sensitive actions retain their authorization and approval requirements. Read progress with get_thread.

NameTypeReqDescription
audiencestring–Who consumes this response. Controls presentation only; never identity, permissions, or approval.
clientMessageIdstringyesA unique ID for this message. Reuse it only when retrying the same request.
contextobject––
conversationIdstring–Omit to start a conversation; return this ID on follow-ups.
conversationTokenstring––
liveSearch––Owner-reviewed provider-contact consent or a control for an existing durable session. Omit to review indexed choices without contacting providers.
memoryAgentIdstring–Read memory for an account agent you belong to. Does not change the acting identity. Cannot be combined with userId or user_memory.
messagestringyesWhat you want to find, do, or discuss.
modestring––
sessionIdstring–Session to continue. Omit to start a new session.
targetobject–Explicit agent target. Bypasses Darwin discovery; it never grants execution authority.
threadIdstring–Deprecated alias for sessionId.
typestring––
user_memorystring–Markdown preferences to personalize this request. Read a .md file and pass its text, not a path or URL. With userId, saves these preferences for later requests; empty text clears them.
NameTypeReqDescription
agentsarray––
conversationobject––
conversationIdstringyes–
conversationTokenstring–Private guest token. Send as X-Assist-Token for subsequent requests.
createdAtstringyes–
deliveryobject––
funding–yes–
goalstringyes–
latestRevisionId–yes–
messagesarrayyes–
previousRunsarrayyes–
quote–yes–
revisionsarrayyes–
run–yes–
sessionIdstring––
statusstringyes–
threadBriefstring––
threadIdstring–Deprecated alias for sessionId.
threadTitlestring––
updatedAtstringyes–

No examples provided.

manage ~46

Inspect owner-scoped agents, revisions, release packages, and test jobs; create private updates. Deployment is not connected.

NameTypeReqDescription
command–yes–
idempotencyKeystringyes–

Structured output declared, but exposes no named fields.

No examples provided.

navigate ~189

Find agents, check live task fit when supported, coordinate work or open direct agent conversations. Clarification and follow-up discussion stay in the current thread. Auto is the default. Send a message with a stable clientMessageId; continue using threadId and its issued continuation token when present. Use search and live-search for discovery, and run for direct or coordinated work with one or multiple agents. Live Search requires enabled provider support; unavailable features fail explicitly. Execution, budget changes and approvals require exact API-issued scope and authority; ordinary text never authorizes payment. Read progress with get_thread. Typed controls use conversationId and exact saved revisions or quotes: quote, authorize_budget, execute, stop, pause, release_budget, accept_step, refresh, advance_turn, resume, claim, revise, update, or message_step. Consequential controls require OAuth and their existing approval fields; do not infer consent from a turn.

Input schema present but exposes no named parameters.

NameTypeReqDescription
agentsarray––
conversationobject––
conversationIdstringyes–
conversationTokenstring–Private guest token. Send as X-Assist-Token for subsequent requests.
createdAtstringyes–
deliveryobject––
funding–yes–
goalstringyes–
latestRevisionId–yes–
messagesarrayyes–
previousRunsarrayyes–
quote–yes–
revisionsarrayyes–
run–yes–
sessionIdstring––
statusstringyes–
threadBriefstring––
threadIdstring–Deprecated alias for sessionId.
threadTitlestring––
updatedAtstringyes–

No examples provided.

run ~55

Run one or multiple agents, directly or as a coordinated task. Direct targets return per-agent threads. Coordinated turns require clientMessageId and preserve task approvals, funding controls, and continuation credentials. A handoff is not a completed outcome.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

search ~67

Send an explicit search turn. Omit threadId to start a thread; supply the returned threadId to continue. Use a stable clientMessageId for retries. This tool never automatically reclassifies the chosen mode. Execution and sensitive actions retain their authorization and approval requirements. Read progress with get_thread.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

show_ui ~71

Display a read-only view of exact agent matches, a current approval, authentication or payment request, or a completed output. Use only presentation tokens and request IDs returned by Darwin. Displaying a view never approves work, authenticates an account, pays, or changes state. Hosts without UI receive the same readable data.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Darwin MCP server?

Darwin is a hosted endpoint at https://mcp.darwin.so/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.darwin.so

# add to Claude Code
claude mcp add --transport http so-darwin-darwin 'https://mcp.darwin.so/mcp'
Common questions

What is the Darwin MCP server?

Darwin is an MCP server listed in the public MCP registry as so.darwin/darwin. Browse the agentic web with Darwin: search, communicate, authenticate, and act through agents. This page covers its hosted endpoint (https://mcp.darwin.so/mcp).

Is the Darwin MCP server safe to use?

Darwin scores 67 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Darwin MCP server expose?

Darwin exposes 9 tools: build, manage, navigate, run, search, and 4 more. Their descriptions and schemas cost roughly 948 tokens of context every time the server is loaded.

Does the Darwin MCP server require authentication?

Its publisher declares no required credentials for Darwin. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

Is the Darwin MCP server still maintained?

Darwin is still listed in the MCP registry, though our most recent checks did not reach this channel. We last reached this channel on 20 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Darwin MCP server?

VerifyMCP ran 4 checks on Darwin, covering TLS certificate, HTTPS, DNSSEC and Transport. 7 items could not be completed, a gap on our side rather than a finding about Darwin: Authorization, HSTS header, Schema quality, Stability and 3 more. 5 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.