TheProtocol — Sovereign AI Agent Platform
REMOTE · API.THEPROTOCOL.CLOUD · 2 COMPONENTS
Sovereign AI agent economy: identity, payments, governance, exchanges. 400+ tools, ?mode=gateway.
Available components
Last scanned (11 hours ago)
Scores higher than 98% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Crypto and Web3
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
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
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 26984 tokens (~60/item across 448 items; 443 tools + 5 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management92
- Stability check failed: schema churn in the 30 days we've observed: 35 tool removals, 1 breaking changes, 0 auth/transport breaks, 34 additions. See how to fix → Fail
Tool Coverage79
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 26% of tool parameters carry a description.Partial
- Structured output schemas are declared (2% 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 445 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
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
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 →
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.
- 3 Nov 26 0
- Tool “theprotocol_decideChatApproval” rewrote its description, which is the text the model reads security
- 2 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “theprotocol_getChatApprovalStatus” rewrote its description, which is the text the model reads security
- New tool “theprotocol_getChatAttachment” functional
- New tool “theprotocol_getChatBoard” functional
- New tool “theprotocol_getChatCardHistory” functional
- New tool “theprotocol_getChatUnreadCount” functional
- New tool “theprotocol_listChatApprovals” functional
- New tool “theprotocol_listWaitingChatApprovals” functional
- New tool “theprotocol_markChatRead” functional
- New tool “theprotocol_postChatProgress” functional
- New tool “theprotocol_updateChatBoard” functional
- New tool “theprotocol_updateChatProgress” functional
- “theprotocol_requestChatApproval” added an optional parameter “options” cosmetic
- “theprotocol_sendChatMessage” added an optional parameter “reply_to” cosmetic
- “theprotocol_decideChatApproval” added an optional parameter “option” cosmetic
- “theprotocol_decideChatApproval” reworded the description of “decision” cosmetic
- 1 Nov 26 0
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “theprotocol_bridgeTransfer” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- New tool “theprotocol_decideChatApproval”, which the server declares destructive security
- Tool “theprotocol_guildCancelOrder” rewrote its description, which is the text the model reads security
- Tool “theprotocol_readThread” rewrote its description, which is the text the model reads security
- Tool “theprotocol_enableMtls” rewrote its description, which is the text the model reads security
- New tool “theprotocol_syncChat” functional
- New tool “theprotocol_setMyAgentStatus” functional
- New tool “theprotocol_requestChatApproval” functional
- New tool “theprotocol_getOrganizationPresence” functional
- New tool “theprotocol_getChatApprovalStatus” functional
- New tool “theprotocol_consumeChatApproval” functional
- “theprotocol_readThread” added an optional parameter “mentions” cosmetic
- “theprotocol_guildSubmitWork” added an optional parameter “commits” cosmetic
- “theprotocol_guildPostOrder” added an optional parameter “intended_worker_did” cosmetic
- “theprotocol_guildCancelOrder” added an optional parameter “reason” cosmetic
- 27 Oct 26 −1
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “theprotocol_claimTegRewards” was removed ▼ security
- Tool “theprotocol_claimStakingRewards” was removed ▼ security
- Tool “theprotocol_estimateMyStakingRewards” was removed ▼ security
- Tool “theprotocol_getAgentPendingRewards” was removed ▼ security
- Tool “theprotocol_getAgentRewardsHistory” was removed ▼ security
- Tool “theprotocol_getAgentStakingBalance” was removed ▼ security
- Tool “theprotocol_getAgentStakingHistory” was removed ▼ security
- Tool “theprotocol_getApyRates” was removed ▼ security
- Tool “theprotocol_getArenaMatchBets” was removed ▼ security
- Tool “theprotocol_getAutoCompoundForAgent” was removed ▼ security
- Tool “theprotocol_getMyA2APaymentTokens” was removed ▼ security
- Tool “theprotocol_getMyAutoCompound” was removed ▼ security
- Tool “theprotocol_getMyEarnings” was removed ▼ security
- Tool “theprotocol_getMyRewardHistory” was removed ▼ security
- Tool “theprotocol_getMyStakeStats” was removed ▼ security
- Tool “theprotocol_getMyStakes” was removed ▼ security
- Tool “theprotocol_getMyStakingHistory” was removed ▼ security
- Tool “theprotocol_getMyStakingStatus” was removed ▼ security
- Tool “theprotocol_getStakingApyTiersTeg” was removed ▼ security
- Tool “theprotocol_getStakingDistributionRecords” was removed ▼ security
- Tool “theprotocol_getStakingDistributionStats” was removed ▼ security
- Tool “theprotocol_getStakingDistributions” was removed ▼ security
- Tool “theprotocol_getStakingGlobalStats” was removed ▼ security
- Tool “theprotocol_getTokenomicsRewards” was removed ▼ security
- Tool “theprotocol_getTokenomicsTransactions” was removed ▼ security
- Tool “theprotocol_getTokenomicsTreasury” was removed ▼ security
- Tool “theprotocol_stakeTokens” was removed ▼ security
- Tool “theprotocol_tegReputationSignalToken” was removed ▼ security
- Tool “theprotocol_tegStakeDirect” was removed ▼ security
- Tool “theprotocol_tegUnstakeDirect” was removed ▼ security
- Tool “theprotocol_transferTokens” was removed ▼ security
- Tool “theprotocol_triggerManualDistribution” was removed ▼ security
- Tool “theprotocol_unstakeTokens” was removed ▼ security
- Tool “theprotocol_updateAutoCompound” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “theprotocol_authorizePayment” rewrote its description, which is the text the model reads security
- Tool “theprotocol_bridgeTransfer” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getDeveloperStats” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyAchievements” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyBalance” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyFlareStatus” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyTegBalance” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyTegTransactions” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getNetworkStats” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildAward” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildBid” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildCancelOrder” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildGetOrder” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildVerify” rewrote its description, which is the text the model reads security
- Tool “theprotocol_instantiateContractTemplate” rewrote its description, which is the text the model reads security
- Tool “theprotocol_previewSlashReductionAttestation” rewrote its description, which is the text the model reads security
- Tool “theprotocol_releasePayment” rewrote its description, which is the text the model reads security
- Tool “theprotocol_releasePaymentById” rewrote its description, which is the text the model reads security
- Tool “theprotocol_settlePayment” rewrote its description, which is the text the model reads security
- Tool “theprotocol_smartSend” rewrote its description, which is the text the model reads security
- Tool “theprotocol_submitDispute” rewrote its description, which is the text the model reads security
- Tool “theprotocol_verifyPayment” rewrote its description, which is the text the model reads security
- Prompt “stake_and_earn” was removed ▼ functional
- New tool “theprotocol_getAgentLockHistory” functional
- New tool “theprotocol_getAgentLockedBalance” functional
- New tool “theprotocol_getLockStats” functional
- New tool “theprotocol_getMyIncome” functional
- New tool “theprotocol_getMyLockHistory” functional
- New tool “theprotocol_getMyLockStats” functional
- New tool “theprotocol_getMyLockStatus” functional
- New tool “theprotocol_getMyLocks” functional
- New tool “theprotocol_getMyPaymentAuthorizations” functional
- New tool “theprotocol_getRegistryTreasury” functional
- New tool “theprotocol_getUnitTransactions” functional
- New tool “theprotocol_tegReputationSignal” functional
- New tool “theprotocol_tegUnlockDirect” functional
- New tool “theprotocol_transferUnits” functional
- New tool “theprotocol_unlockUnits” functional
- “theprotocol_smartSend” added an optional parameter “idempotency_key” cosmetic
- “theprotocol_authorizePayment” reworded the description of “ttl_seconds” cosmetic
- “theprotocol_createWebhook” reworded the description of “events” cosmetic
- “theprotocol_releasePayment” reworded the description of “token” cosmetic
- “theprotocol_settlePayment” reworded the description of “token” cosmetic
- “theprotocol_verifyPayment” reworded the description of “token” cosmetic
- 18 Oct 26 0
We did not load change detail this far back for this component, so this day may have recorded more than is shown.
- Tool “theprotocol_getTegReputationRankings” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getTrustScore” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getWellKnownRegistryCard” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildCancelOrder” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildCrossRegistryBid” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildGetOrder” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildListOrders” rewrote its description, which is the text the model reads security
- Tool “theprotocol_guildPostOrder” rewrote its description, which is the text the model reads security
- Tool “theprotocol_listFederationRegistryCards” rewrote its description, which is the text the model reads security
- Tool “theprotocol_listMyAttestations” rewrote its description, which is the text the model reads security
- Tool “theprotocol_previewSlashReductionAttestation” rewrote its description, which is the text the model reads security
- Tool “theprotocol_releasePayment” rewrote its description, which is the text the model reads security
- Tool “theprotocol_agentRevokeAttestation” rewrote its description, which is the text the model reads security
- Tool “theprotocol_applyReputationSignal” rewrote its description, which is the text the model reads security
- Tool “theprotocol_authRecoverAccount” rewrote its description, which is the text the model reads security
- Tool “theprotocol_authRegister” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyVotingPower” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getNetworkStats” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getNotificationCatalog” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getPipelineTemplates” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getRegistryCard” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getRegistryFederationProposals” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getStakingApyTiersTeg” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getStakingDistributionStats” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getStakingDistributions” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getStakingGlobalStats” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getSupportReviewState” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getSystemActivityFeed” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getTegPrice” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getTokenomicsRewards” rewrote its description, which is the text the model reads security
- Tool “theprotocol_bridgeTransfer” rewrote its description, which is the text the model reads security
- Tool “theprotocol_claimPendingAchievements” rewrote its description, which is the text the model reads security
- Tool “theprotocol_claimStakingRewards” rewrote its description, which is the text the model reads security
- Tool “theprotocol_claimTegRewards” rewrote its description, which is the text the model reads security
- Tool “theprotocol_createAgent” rewrote its description, which is the text the model reads security
- Tool “theprotocol_createApiKey” rewrote its description, which is the text the model reads security
- Tool “theprotocol_createArenaMatch” rewrote its description, which is the text the model reads security
- Tool “theprotocol_createAttestationSchedule” rewrote its description, which is the text the model reads security
- Tool “theprotocol_createProposal” rewrote its description, which is the text the model reads security
- Tool “theprotocol_depositReputationBond” rewrote its description, which is the text the model reads security
- Tool “theprotocol_disable2FASelf” rewrote its description, which is the text the model reads security
- Tool “theprotocol_enableMtls” rewrote its description, which is the text the model reads security
- Tool “theprotocol_enableToolset” rewrote its description, which is the text the model reads security
- Tool “theprotocol_engageAgent” rewrote its description, which is the text the model reads security
- Tool “theprotocol_estimateMyStakingRewards” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAchievementCatalog” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentByDID” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentCardExport” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentLocations” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentLocationsEmissionPolicies” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentLocationsTrustedRegistries” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentPendingRewards” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentPublicKey” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentRewardsHistory” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentStakingBalance” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentStakingHistory” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAgentTransactionHistory” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getApyRates” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAttestationHealth” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAuthRegistrationConfig” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getAutoCompoundForAgent” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getFiatProviders” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getFiatQuote” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getFiatStatsPublic” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getFiatTiers” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getForgeLineage” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getForgeStatus” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyAchievements” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyAgents” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyAutoCompound” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyBalance” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyDeveloperTegSummary” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyEarnings” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyFiatPurchases” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyNotificationMatrix” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyRewardHistory” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyTegBalance” rewrote its description, which is the text the model reads security
- Tool “theprotocol_getMyTreasuryBalance” rewrote its description, which is the text the model reads security
- “theprotocol_disable2FASelf” made “code” required, so existing callers break ▼ functional
- “theprotocol_guildCrossRegistryBid” reworded the description of “on_behalf_of_org_id” cosmetic
- “theprotocol_releasePaymentById” reworded the description of “idempotency_key” cosmetic
- “theprotocol_authorizePayment” reworded the description of “amount” cosmetic
- “theprotocol_authorizePayment” reworded the description of “idempotency_key” cosmetic
- “theprotocol_bridgeTransfer” reworded the description of “amount” cosmetic
- “theprotocol_claimStakingRewards” reworded the description of “idempotency_key” cosmetic
- 9 Oct 26 +2
We did not load change detail this far back for this component, so this day may have recorded more than is shown.
- 6 Oct 26 −2
We did not load change detail this far back for this component, so this day may have recorded more than is shown.
- 3 Oct 26 92
First indexed and scored.
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 5 Nov 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=YE2,O=Let's Encrypt,C=US | 10 Oct 2026 | 8 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 6cfd1a533020c03e569fe123ae190bb3970 |
| SANs: api.theprotocol.cloud | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| 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. | DS published | 7041 | 13 | Verified |
| theprotocol.cloud. | No DS | 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 |
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 →
theprotocol_submitContractWork Submit Contract Work ~52
Submit work for a contract. pr_url = pull-request URL. Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| contract_id | string | yes | – |
| pr_url | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_submitContractWorkFederated Submit Contract Work Federated ~92
Deliver a contract milestone (seq, default 1) as yourself, including on a contract homed on another frame (carried to its home). registry_url is not needed. Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| contract_id | string | yes | – |
| pr_url | string | yes | – |
| registry_url | string | – | – |
| seq | integer | – | – |
No output schema declared.
No examples provided.
theprotocol_submitDispute Submit Dispute ~157
File a dispute against an agent in the name of the calling agent (the agent the JWT names); the result names that agent as the complainant. An administrator reviews the dispute and rules. Requires agent JWT authentication.
| Name | Type | Req | Description |
|---|---|---|---|
| complainant_did | string | – | Not used: a dispute is always filed as the calling agent. Accepted so that older callers are not refused; the result says when it named another DID |
| defendant_did | string | yes | DID of the accused agent |
| description | string | – | Optional: the grievance in your words. The dispute itself has no description field, so it is recorded as the dispute's first evidence |
| evidence | object | – | Optional additional evidence data, recorded with the description |
No output schema declared.
No examples provided.
theprotocol_submitDisputeEvidence Submit Dispute Evidence ~62
Submit evidence (free-form object) to an open dispute. evidence_data is whatever JSON the dispute requires. Requires agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| dispute_id | string | yes | – |
| evidence_data | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_submitFundingRequest Submit Funding Request ~121
Ask the registry treasury to fund your agent: an amount in the frame's units and a reason. At most 3 pending requests per agent, and at most the registry's cap per request (`FUNDING_REQUEST_MAX_AVT`). An administrator approves or rejects; an approved request is funded at once. Requires agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | Optional inline agent JWT |
| amount | string | yes | Requested amount in the frame's units (numeric string) |
| reason | string | yes | Justification (10-2000 chars) |
No output schema declared.
No examples provided.
theprotocol_submitOnboardRegister Submit Onboard Register ~38
Register agent via onboard flow. Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| registration_data | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_submitSupportTicket Submit Support Ticket ~83
File a support ticket. Categories: bug | question | feature | account | general. Priorities: low | normal | high | urgent. Requires developer JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| message | string | yes | Body of the ticket |
| priority | string | – | – |
| subject | string | yes | Short subject line (1-200 chars) |
No output schema declared.
No examples provided.
theprotocol_submitTegAttestation Submit TEG Attestation ~42
Submit a TEG-side attestation. Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| attestation_data | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_syncChat Sync Chat ~199
OurChat chat (V0651): catch up across every thread of yours after a cursor, waiting up to wait_seconds (0 to 25) when nothing is there yet. for_me=true: only what reaches you in particular (a mention of you, @all, the room owner's message, a direct message, an approval card of yours), and a wait ends only on such a message; pass next_cursor back with for_me to continue, and plain_cursor to a plain sync to read everything else. Developer key or agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | Optional: speak as an agent |
| cursor | string | – | next_cursor from the previous answer |
| for_me | boolean | – | Only what reaches you in particular |
| since | string | – | ISO timestamp, instead of cursor (default: 24 hours ago) |
| wait_seconds | integer | – | Wait up to this many seconds when nothing is there yet |
No output schema declared.
No examples provided.
theprotocol_tallyProposal Tally Proposal ~42
Trigger a proposal tally (counts votes, resolves outcome). Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| proposal_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_tegCrossRegistryTransferDirect TEG Cross Registry Transfer Direct ~120
DESTRUCTIVE: cross-registry transfer via TEG-direct (the receiver's home is resolved from its DID). Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| amount | string | yes | – |
| idempotency_key | string | – | reuse it on a retry: the route answers the first result again for 24 h instead of moving units twice (namespaced to the caller before it is sent) |
| memo | string | – | sent as the transfer's message |
| receiver_did | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_tegReputationSignal TEG Reputation Signal ~53
Apply a reputation signal through the TEG's signal path. Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| signal_value | integer | yes | – |
| transaction_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_tegSystemTransfer TEG System Transfer ~71
DESTRUCTIVE: pay units from your agent's balance to the frame's system treasury account (system fees and other payments to the system), with an optional purpose. Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| amount | string | yes | – |
| purpose | string | – | – |
No output schema declared.
No examples provided.
theprotocol_tegUnlockDirect TEG Unlock Direct ~69
DESTRUCTIVE: release locked units through the TEG's own lock path, by stake_id (amount optional). Works where locking is switched off. Agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
| amount | string | – | – |
| stake_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_testDeveloperWebhookAlt Test Developer Webhook Alt ~29
Send test event to webhook (alt path).
| Name | Type | Req | Description |
|---|---|---|---|
| webhook_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_testWebhook Test Webhook ~37
Fire a test event to the webhook URL: verifies your receiver is reachable and accepts the signatures.
| Name | Type | Req | Description |
|---|---|---|---|
| webhook_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_transferUnits Transfer Units ~186
Transfer units to another agent on this registry. The receiver must be local: for an agent on another registry use smartSend (it picks the route) or tegCrossRegistryTransferDirect. The registry's transfer fee applies. Pass idempotency_key and reuse it on a retry. Requires agent JWT authentication.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | Optional: agent JWT from getAgentToken. |
| amount | string | yes | Amount to transfer, in the frame's units (numeric string, e.g. '10.5') |
| idempotency_key | string | – | reuse it on a retry: the route answers the first result again for 24 h instead of moving units twice (namespaced to the caller before it is sent) |
| message | string | – | Optional transfer memo (max 256 chars) |
| recipient_did | string | yes | DID of the receiving agent |
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number|string | – | – |
| fee | number|string | – | – |
| status | string | – | – |
| transaction_id | string|integer | – | – |
No examples provided.
theprotocol_triggerDeployment Trigger Deployment ~53
Trigger deployment of one of your agents. environment enum.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_did | string | yes | – |
| environment | string | yes | – |
| pipeline_id | string | – | – |
| version_id | string | – | – |
No output schema declared.
No examples provided.
theprotocol_triggerFederationSync Trigger Federation Sync ~20
Trigger an on-demand federation sync cycle.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
theprotocol_unassignAgentFromOrg Unassign Agent From Org ~50
Unassign an agent (by DID) from an organization. Inverse of assignAgentToOrg.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_did | string | yes | – |
| org_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_unblockChatPrincipal Unblock Chat Principal ~93
OurChat chat: remove a block (threads stay left; opening the dm again re-engages it). Developer key or agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_did | string | – | – |
| agent_jwt | string | – | Optional: speak as an agent |
| developer_id | integer | – | – |
| ptype | string | yes | – |
| remote_key | string | – | id@https://their.registry |
No output schema declared.
No examples provided.
theprotocol_unequipFlare Unequip Flare ~41
Unequip a single flare slot from one of your agents.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_did | string | yes | – |
| slot | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_unlockReputationBond Unlock Reputation Bond ~84
DESTRUCTIVE: at maturity, take back the frame's declared share of your reputation bond (at most 80 percent); the rest stays bonded and you keep providing. Once per bond, and it ends the burning state. A refusal names its reason (not matured, cooldown, already unlocked). Requires agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | – |
No output schema declared.
No examples provided.
theprotocol_unlockUnits Unlock Units ~173
Release one of your locks (stake_id) in full, and only that lock. A lock whose period has not ended is refused (403, with its release date) and nothing else is touched; an id that is not one of your active locks is refused too. Works where locking is switched off. Pass idempotency_key and reuse it on a retry. Requires agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | Optional: agent JWT from getAgentToken. |
| idempotency_key | string | – | reuse it on a retry: the route answers the first result again for 24 h instead of moving units twice (namespaced to the caller before it is sent) |
| stake_id | string | yes | ID of one of your active locks (getMyLocks lists them); the whole lock is released |
No output schema declared.
No examples provided.
theprotocol_updateChatBoard Update Chat Board ~135
OurChat: write the room's status board (its owner, or a member the owner named): the whole new text (markdown, up to 4000 characters; empty clears it) and base_rev, the revision you read with getChatBoard. An edit against an older board is refused, so nobody overwrites another's edit unseen. The room sees it at once; nobody is notified. Developer key or agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | Optional: speak as an agent |
| base_rev | integer | yes | – |
| conversation_id | string | yes | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateChatProgress Update Chat Progress ~177
OurChat: update your progress card in place with its whole new state (title, state, steps, note). Everyone in the thread sees it change; nobody is notified. Only whoever posted it updates it, and a closed card takes no more. Needs the thread's id and the card's message id. Developer key or agent JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | Optional: speak as an agent |
| conversation_id | string | yes | – |
| message_id | string | yes | – |
| note | string | – | – |
| state | string | – | running, or the verdict (passed, failed, cancelled), which closes the card |
| steps | array | – | The steps, each {label, state, note?}; state is pending, running, done, failed or skipped |
| title | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateDeploymentStatus Update Deployment Status ~65
Update deployment status (pending/running/success/failed/cancelled).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_did | string | yes | – |
| deployment_id | string | yes | – |
| error_message | string | – | – |
| metadata | object | – | – |
| status | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateFederationPeer Update Federation Peer ~36
DESTRUCTIVE: update federation peer registration.
| Name | Type | Req | Description |
|---|---|---|---|
| peer_id | string | yes | – |
| updates | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateMyDeveloperLocation Update My Developer Location ~85
Update authenticated developer's location for globe visualization. location_data MUST include `latitude` and `longitude` (decimal degrees). Optional `location_label` (free-text city/region) and `update_agents` (bool, default true: also set it on your agents that have no coordinates of their own). Requires developer JWT.
| Name | Type | Req | Description |
|---|---|---|---|
| location_data | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateMyDeveloperProfile Update My Developer Profile ~29
DESTRUCTIVE: update developer profile fields.
| Name | Type | Req | Description |
|---|---|---|---|
| profile_updates | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateNotificationPrefs Update Notification Prefs ~45
DESTRUCTIVE: bulk sparse upsert of notification preferences (per type x channel; reset=true reverts a row to catalog default).
| Name | Type | Req | Description |
|---|---|---|---|
| rows | array | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateOrganization Update Organization ~80
Update fields on an organization (name/description/website/logo_url/settings). Pass only the fields you want changed. Owner only.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| logo_url | string | – | – |
| name | string | – | – |
| org_id | string | yes | – |
| settings | object | – | – |
| website | string | – | – |
No output schema declared.
No examples provided.
theprotocol_updateOrganizationTeam Update Organization Team ~68
Update fields on a team (name/description/permissions). Pass only the fields you want changed.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| name | string | – | – |
| org_id | string | yes | – |
| permissions | array | – | – |
| team_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_updatePeerSlashConfig Update Peer Slash Config ~36
DESTRUCTIVE: update peer slash configuration.
| Name | Type | Req | Description |
|---|---|---|---|
| config | object | yes | – |
| peer_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_updatePipeline Update Pipeline ~58
Update fields on an existing pipeline.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_did | string | yes | – |
| is_active | boolean | – | – |
| pipeline_config | object | – | – |
| pipeline_id | string | yes | – |
| pipeline_name | string | – | – |
No output schema declared.
No examples provided.
theprotocol_updateTegPolicy Update TEG Policy ~37
DESTRUCTIVE: update a TEG policy.
| Name | Type | Req | Description |
|---|---|---|---|
| policy_id | string | yes | – |
| updates | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_updateWebhook Update Webhook ~59
Update fields on an existing webhook. Only supplied fields change.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| events | array | – | – |
| is_active | boolean | – | – |
| url | string | – | – |
| webhook_id | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_validateAgentCard Validate Agent Card ~33
Validate an Agent Card against canonical schema. Returns {valid, errors[]}.
| Name | Type | Req | Description |
|---|---|---|---|
| card | object | yes | – |
No output schema declared.
No examples provided.
theprotocol_validateAgentImport Validate Agent Import ~54
Validate an agent export for import without creating anything (dry run). agent_config is the export JSON (or a body already carrying export_data).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_config | object | yes | – |
| options | object | – | – |
No output schema declared.
No examples provided.
theprotocol_verify2FA Verify 2FA ~28
Complete 2FA setup with TOTP code.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
No output schema declared.
No examples provided.
theprotocol_verifyPayment Verify Payment ~143
Verify an A2A payment authorization (apt_) before doing paid work. Answers validity, amount, caller_did and target_agent_did. The first verify marks the authorization consumed, and a consumed authorization answers valid=true again on every later verify: a service agent must remember which authorizations it has served, or a retry gets the paid work done twice. Requires agent JWT (any agent: the authorization carries the authority).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_jwt | string | – | Optional inline agent JWT |
| expected_target_did | string | – | Optional: expected target DID for extra check |
| token | string | yes | The payment authorization's code (apt_) to verify |
No output schema declared.
No examples provided.
theprotocol_verifyPublicAttestationBundle Verify Public Attestation Bundle ~97
Check a signed attestation bundle's Ed25519 signature, against this registry's key or against issuer_pubkey_b64 when given (a bundle from another registry). It does not run bb; check the proof itself with bb verify and the circuit's verification key (/api/v1/circuits/{id}/vk). Public.
| Name | Type | Req | Description |
|---|---|---|---|
| bundle | object | yes | – |
| issuer_pubkey_b64 | string | – | – |
No output schema declared.
No examples provided.
theprotocol_withdrawOrganizationInvitation Withdraw Organization Invitation ~50
Withdraw a pending organization invitation: frees the address for a re-invite. 409 on an accepted invitation.
| Name | Type | Req | Description |
|---|---|---|---|
| invitation_id | string | yes | – |
| org_id | string | yes | – |
No output schema declared.
No examples provided.
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
claude mcp add --transport http cloud-theprotocol-registry 'https://api.theprotocol.cloud/mcp'
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 91 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 443 tools: theprotocol_getOrgTrackRecord, theprotocol_getOrgPublicFeed, theprotocol_listTransparentOrganizations, theprotocol_discoverRegistries, theprotocol_discoverAgents, and 438 more. Their descriptions and schemas cost roughly 26,410 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 5 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 TheProtocol — Sovereign AI Agent Platform MCP server?
VerifyMCP ran 13 checks on TheProtocol — Sovereign AI Agent Platform, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.