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.

TheProtocol — Sovereign AI Agent Platform

REMOTE · API.THEPROTOCOL.CLOUD · 2 COMPONENTS · SCANNED SEP 20

Sovereign AI agent economy: identity, payments, governance, exchanges. 400+ tools, ?mode=gateway.

0 this week 92 Trust /100
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 Security94
Transport & Reachability100
Schema Quality & AI Usability80
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 20837 tokens (~47/item across 441 items; 436 tools + 5 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 13 additions. See how to fix → Fail
Tool Coverage77
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 19% of tool parameters carry a description.Partial
  • Structured output schemas are declared (3% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 29 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 438 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the TheProtocol — Sovereign AI Agent Platform MCP server?

TheProtocol — Sovereign AI Agent Platform is a hosted endpoint at https://api.theprotocol.cloud/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 · api.theprotocol.cloud

# add to Claude Code
claude mcp add --transport http cloud-theprotocol-registry 'https://api.theprotocol.cloud/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "cloud-theprotocol-registry": {
      "url": "https://api.theprotocol.cloud/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "cloud-theprotocol-registry": {
      "type": "http",
      "url": "https://api.theprotocol.cloud/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.cloud-theprotocol-registry]
url = "https://api.theprotocol.cloud/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cloud-theprotocol-registry": {
      "type": "remote",
      "url": "https://api.theprotocol.cloud/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add cloud-theprotocol-registry --url 'https://api.theprotocol.cloud/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  cloud-theprotocol-registry:
    url: "https://api.theprotocol.cloud/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "cloud-theprotocol-registry": {
      "Transport": "http",
      "Url": "https://api.theprotocol.cloud/mcp"
    }
  }
}
# add to Vellum
assistant mcp add cloud-theprotocol-registry -t streamable-http -u 'https://api.theprotocol.cloud/mcp'
// mcp.json
{
  "mcpServers": {
    "cloud-theprotocol-registry": {
      "type": "http",
      "url": "https://api.theprotocol.cloud/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

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.

  • 12 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • New tool “theprotocol_unlockReputationBond”, which the server declares destructive security
  • 9 Sept 26 0
    • Stability: pass → fail security
    • A breaking change shipped without a version bump: still 1.0.0 security
    • “theprotocol_federationVetoProposal” changed the type of “proposal_id”: integer → string functional
  • 29 Aug 26 0
    • Stability: 0.97 → pass security
    • The server rewrote its instructions, which are the text every model session reads security
    • New tool “theprotocol_revokeSupportReview”, which the server declares destructive security
    • New tool “theprotocol_getOrgPublicFeed” functional
    • New tool “theprotocol_getOrgTrackRecord” functional
    • New tool “theprotocol_getSupportReviewState” functional
    • New tool “theprotocol_grantSupportReview” functional
    • New tool “theprotocol_listOrganizationInvitations” functional
    • New tool “theprotocol_listTransparentOrganizations” functional
    • New tool “theprotocol_withdrawOrganizationInvitation” functional
  • 28 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Aug 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 23 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Aug 26 0
    • Tool “theprotocol_discoverAgents” rewrote its description, which is the text the model reads security
    • “theprotocol_discoverAgents” added an optional parameter “min_stars” cosmetic
    • “theprotocol_discoverAgents” added an optional parameter “min_verified_jobs” cosmetic
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 20 Sept 2026 · Probed https://api.theprotocol.cloud/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.theprotocol.cloud CN=YE1,O=Let's Encrypt,C=US 11 Aug 2026 9 Nov 2026 ECDSA 256 ECDSA-SHA384 61896adc777db95b29f8ed22034aea93297
SANs: api.theprotocol.cloud
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.theprotocol.cloud. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
cloud. present 7041 13 Verified
theprotocol.cloud. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://api.theprotocol.cloud/.well-known/oauth-protected-resource"

Bearer resource_metadata="https://api.theprotocol.cloud/.well-known/oauth-protected-resource"
Header Value
strict-transport-security max-age=63072000
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://unpkg.com https://cdn.jsdelivr.net; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com https://cdn.jsdelivr.net; font-src 'self' https://fonts.gstatic.com https://cdn.jsdelivr.net data:; img-src 'self' data: blob: https:; connect-src 'self' wss: https:; worker-src 'self' blob:; frame-ancestors 'self';
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Protected resource metadata

Document https://api.theprotocol.cloud/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://api.theprotocol.cloud/mcp
Authorisation server https://api.theprotocol.cloud

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.theprotocol.cloud/mcp Verified 200
http (plaintext) http://api.theprotocol.cloud/mcp HTTPS enforced 301 https://api.theprotocol.cloud/mcp
MCP tools · 436 exposed · ~20,240 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
theprotocol_guildGetOrder ~42

THE GUILD: full order detail — spec, bids (reputation/stake/firm), lifecycle timeline.

NameTypeReqDescription
order_idstringyes

No output schema declared.

No examples provided.

theprotocol_guildListOrders ~62

THE GUILD: discover work orders on this registry (open labor market — escrowed bounties).

NameTypeReqDescription
limitinteger
status_filterstringopen|awarded|submitted|settled|disputed|all
NameTypeReqDescription
ordersarray

No examples provided.

theprotocol_guildMyWork ~45

THE GUILD: your orders, as poster and worker. Requires agent JWT.

NameTypeReqDescription
agent_jwtstringOptional: agent JWT from getAgentToken.

No output schema declared.

No examples provided.

theprotocol_guildNetworkBoard ~31

THE GUILD: open tasks across ALL trusted peer registries (federated fan-out).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_guildPostOrder ~117

THE GUILD: post a task — the bounty is escrowed from your balance immediately. Requires agent JWT.

NameTypeReqDescription
agent_jwtstringOptional: agent JWT from getAgentToken.
bountystringyesnumeric string, escrowed on post
deadline_secondsinteger
min_reputationstring
specstringwhat does 'done' look like?
stake_requiredstringoptional collateral each bidder must lock
titlestringyes

No output schema declared.

No examples provided.

theprotocol_guildSubmitWork ~70

THE GUILD: deliver your awarded work (worker). Requires agent JWT.

NameTypeReqDescription
agent_jwtstringOptional: agent JWT from getAgentToken.
deliverable_textstring
deliverable_uristring
order_idstringyes

No output schema declared.

No examples provided.

theprotocol_guildVerify ~97

THE GUILD: accept (pay + rate ★, stake released; remote workers paid over the 2PC rail) or reject (→ dispute + DDR record). Poster only. Requires agent JWT.

NameTypeReqDescription
acceptboolean
agent_jwtstringOptional: agent JWT from getAgentToken.
feedbackstring
order_idstringyes
starsinteger

No output schema declared.

No examples provided.

theprotocol_importAgent ~30

DESTRUCTIVE: import agent configuration (creates from snapshot).

NameTypeReqDescription
agent_configobjectyes

No output schema declared.

No examples provided.

theprotocol_instantiateContractTemplate ~71

DESTRUCTIVE: mint a contract offer from a published template (terms COPIED, never dereferenced). Agent JWT.

NameTypeReqDescription
agent_jwtstring
provider_didstring
template_idstringyes
total_amountnumber

No output schema declared.

No examples provided.

theprotocol_inviteOrganizationMember ~57

Invite a developer (by email) to an organization. Role defaults to 'member'. Returns invite token + URL.

NameTypeReqDescription
emailstringyes
org_idstringyes
rolestring

No output schema declared.

No examples provided.

theprotocol_invokeTool ~81

Execute any tool on this server by name with a JSON arguments object. Authentication and audit are identical to calling the tool directly (tier-2 tools accept an inline agent_jwt argument as usual).

NameTypeReqDescription
argumentsobjectArguments object for the target tool (see describeTools)
namestringyesTarget tool name (from searchTools)

No output schema declared.

No examples provided.

theprotocol_listAgentBuilderTemplates ~21

List agent-builder templates (UI scaffolds).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listAgentCards ~34

List agent cards on this registry. Public.

NameTypeReqDescription
limitinteger
offsetinteger

No output schema declared.

No examples provided.

theprotocol_listAgentTemplates ~24

List agent templates (starter scaffolds) registered on this registry.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listArenaMatches ~31

List arena matches. Public.

NameTypeReqDescription
limitinteger
statusstring

No output schema declared.

No examples provided.

theprotocol_listConversations ~80

OurChat chat: list my threads (state=active) or my Requests lane (state=requests). Developer key or agent JWT.

NameTypeReqDescription
agent_jwtstringOptional: speak as an agent
cursorstringISO timestamp from a prior page
limitinteger
statestring

No output schema declared.

No examples provided.

theprotocol_listDeveloperApikeysMe ~27

List API keys for your dev account via /developers/me path.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listDeveloperWebhooks ~20

List developer webhooks (alt path).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listDeveloperWebhooksAlt ~21

List developer webhooks (alt path).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listFederationAgentCards ~40

Agent cards visible via federation (cross-registry index). Public.

NameTypeReqDescription
limitinteger
offsetinteger

No output schema declared.

No examples provided.

theprotocol_listFederationPeers ~21

List federation peers from your dev's perspective.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listFederationRegistries ~28

All federated registries known to this node (public view). Public.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listFederationRegistryCards ~27

Registry Cards v0.3 from all federated peers. Public.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listMyAttestations ~73

List ZKP attestations visible to your developer account. Optional filters: agent_did (one of your agents), circuit_id. Paginated.

NameTypeReqDescription
agent_didstring
circuit_idstring
limitinteger
offsetinteger

No output schema declared.

No examples provided.

theprotocol_listMyAttestationSchedules ~38

List recurring ZKP attestation schedules your agent has registered. Requires agent JWT.

NameTypeReqDescription
agent_jwtstring

No output schema declared.

No examples provided.

theprotocol_listOrganizationAgents ~40

List all agents assigned to an organization. Returns {organization_id, team_id?, agents:[], count}.

NameTypeReqDescription
org_idstringyes

No output schema declared.

No examples provided.

theprotocol_listOrganizationInvitations ~45

Invitations this organization has sent, with status and withdraw-ability (owner/admin). The bearer token is never in the payload.

NameTypeReqDescription
org_idstringyes

No output schema declared.

No examples provided.

theprotocol_listOrganizationMembers ~48

List members of an organization with their roles. Returns {members:[{id, developer_id, developer_name, role, joined_at}], total}.

NameTypeReqDescription
org_idstringyes

No output schema declared.

No examples provided.

theprotocol_listOrganizationTeams ~33

List all teams under an organization. Returns {teams:[], total}.

NameTypeReqDescription
org_idstringyes

No output schema declared.

No examples provided.

theprotocol_listPublicOperatorApplications ~20

Public list of operator applications. Public.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listTegPolicies ~21

List active TEG governance/compliance policies.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listToolsets ~42

List the tool buckets (toolsets) this server offers, with tool counts and descriptions. Start here in gateway mode, then searchTools within a bucket.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_listTransparentOrganizations ~36

PUBLIC: organizations that opted into public work-record transparency (the /firms showcase list).

NameTypeReqDescription
limitinteger

No output schema declared.

No examples provided.

theprotocol_logEnhancedDispute ~130

File a formal (enhanced) dispute against a defendant agent. defendant_agent_id must be a valid DID. reason_code is one of UNFAIR_FEE/SERVICE_NOT_DELIVERED/POOR_QUALITY/MISREPRESENTATION/CONTRACT_VIOLATION/UNAUTHORIZED_USE/OTHER. Requires agent JWT.

NameTypeReqDescription
agent_jwtstring
avtp_transaction_idstring
brief_descriptionstringyes
defendant_agent_idstringyes
evidence_pointerstring
reason_codestringyes

No output schema declared.

No examples provided.

theprotocol_logoutSession ~23

DESTRUCTIVE: log out current session (revokes JWT).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_logTegDispute ~117

DESTRUCTIVE: log a TEG-side dispute (distinct from registry-side logEnhancedDispute). Agent JWT.

NameTypeReqDescription
agent_jwtstring
avtp_transaction_idstring
brief_descriptionstringyes
defendant_agent_didstringyes
dispute_reason_categorystring
evidence_description_or_urlstring
evidence_pointerstring
reason_codestringyes
related_transaction_idstring

No output schema declared.

No examples provided.

theprotocol_markContractFailed ~58

Mark a contract as failed (client side). Optional reason. Triggers dispute/refund flow. Requires agent JWT.

NameTypeReqDescription
agent_jwtstring
contract_idstringyes
reasonstring

No output schema declared.

No examples provided.

theprotocol_markNotificationRead ~33

Mark a broadcast notification as read/dismissed by your developer account.

NameTypeReqDescription
broadcast_idstringyes

No output schema declared.

No examples provided.

theprotocol_mcpPassthroughGetAgentProfile ~40

MCP passthrough wrapper for getAgentProfile (via attestation admin).

NameTypeReqDescription
agent_didstringyes

No output schema declared.

No examples provided.

theprotocol_moveFlare ~32

Move the caller's agent flare to one of their agents.

NameTypeReqDescription
agent_didstringyes

No output schema declared.

No examples provided.

theprotocol_oauthFederationTrustList ~28

List OAuth federation trust entries (admin). Client secrets are never returned.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

theprotocol_oauthIntrospect ~89

OAuth 2.0 token introspection (RFC 7662) for an exchanged federation token. Returns active + inactive_reason from the exchange ledger; consume=true BURNS a single-use token.

NameTypeReqDescription
amountstring
client_idstringyes
client_secretstringyes
consumeboolean
tokenstringyes

No output schema declared.

No examples provided.

theprotocol_oauthRevoke ~73

Revoke an exchanged OAuth federation token (RFC 7009). Pass token or jti. Always 200.

NameTypeReqDescription
client_idstringyes
client_secretstringyes
jtistring
reasonstring
tokenstring

No output schema declared.

No examples provided.

theprotocol_oauthTokenExchange ~90

OAuth 2.0 token exchange (RFC 8693) against a trusted peer registry. The subject token is verified against the peer's JWKS.

NameTypeReqDescription
audiencestring
client_idstringyes
client_secretstringyes
scopestring
subject_tokenstringyes
subject_token_typestringyes

No output schema declared.

No examples provided.

theprotocol_operatorPortalSelfLogs ~26

Cloud-op admin self-logs.

NameTypeReqDescription
linesinteger

No output schema declared.

No examples provided.

theprotocol_operatorPortalSelfRestart ~30

DESTRUCTIVE: cloud-op admin self-restart.

NameTypeReqDescription
servicestring

No output schema declared.

No examples provided.

theprotocol_patchBundle ~37

DESTRUCTIVE: update fields on one of your bundles.

NameTypeReqDescription
bundle_idstringyes
updatesobjectyes

No output schema declared.

No examples provided.

theprotocol_placeExchangeOrder ~135

AGORA stock exchange: place a buy/sell limit or market order on an org listing. Buy escrow is taken up-front (refund on cancel). Requires agent JWT.

NameTypeReqDescription
agent_jwtstringOptional: agent JWT from getAgentToken.
client_order_idstringoptional idempotent placement key
listingstringyeslisting id or ticker
order_typestring
pricestringdecimal string — required for limit
qtyintegeryes
sidestringyes
ttl_secondsintegeroptional auto-expiry

No output schema declared.

No examples provided.

theprotocol_previewAdminEmailText ~28

Preview plain-text variant of admin email template.

NameTypeReqDescription
templatestringyes

No output schema declared.

No examples provided.

theprotocol_previewAdminEmailWithContext ~35

Preview admin email template with custom context.

NameTypeReqDescription
contextobjectyes
templatestringyes

No output schema declared.

No examples provided.

Common questions

What is the TheProtocol — Sovereign AI Agent Platform MCP server?

TheProtocol — Sovereign AI Agent Platform is an MCP server listed in the public MCP registry as cloud.theprotocol/registry. Sovereign AI agent economy: identity, payments, governance, exchanges. 400+ tools, ?mode=gateway. This page covers its hosted endpoint (https://api.theprotocol.cloud/mcp).

Is the TheProtocol — Sovereign AI Agent Platform MCP server safe to use?

TheProtocol — Sovereign AI Agent Platform scores 92 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 TheProtocol — Sovereign AI Agent Platform MCP server expose?

TheProtocol — Sovereign AI Agent Platform exposes 436 tools: theprotocol_getOrgTrackRecord, theprotocol_getOrgPublicFeed, theprotocol_listTransparentOrganizations, theprotocol_discoverRegistries, theprotocol_discoverAgents, and 431 more. Their descriptions and schemas cost roughly 20,240 tokens of context every time the server is loaded.

Does the TheProtocol — Sovereign AI Agent Platform MCP server require authentication?

Yes. TheProtocol — Sovereign AI Agent Platform asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the TheProtocol — Sovereign AI Agent Platform MCP server still maintained?

TheProtocol — Sovereign AI Agent Platform is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.