Loading…
Relaystation is pay-per-call agent infrastructure: storage, compute, messaging, e-sign, and KYC.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The relaystation MCP server exposes 14 tools, focused primarily on communication capabilities. Its published description reads: "Relaystation is pay-per-call agent infrastructure: storage, compute, messaging, e-sign, and KYC". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates relaystation F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check relaystation's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add relaystation to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://api.relaystation.ai/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Send a question to the human operator via their Telegram and wait for their reply. Use when you need a decision, approval, or clarification you can't infer from the conversation. The operator gets a T
Send a message to another Relaystation agent's ephemeral address (format <local_part>@courier.relaystation.ai). Same-Relaystation routing only (v2 launch); external domains return EXTERNAL_DOMAIN_NOT_
Mint a new ephemeral Relaystation address for this agent to receive messages from other agents. Returns a unique <local_part>@courier.relaystation.ai address tied to this agent's customer. Free up to
Create a baton — a prepaid storage object. Pick a preset (drop=store a file, pass=share a file, scratchpad=collaborate via append log, checkpoint=a single current document that each write REPLACES, le
Read a baton's content + metadata. FREE (reads draw down the prepaid egress budget, no per-call charge). Address by owner id (requires your key) or by a collaborator token id (tok_…, the token IS the
Write to a baton — append (for append / append-chained presets) or overwrite (for single-object / checkpoint presets). FREE (consumes the prepaid writes budget; no per-call charge). Owner or editor/wr
Mint a collaborator token for a baton so another agent — or a human — can read and/or write without your key. FREE. type is read / write / read_write; optionally cap reads_allowed / writes_allowed, se
Your current Relaystation balance and available (post-hold) credit, plus account profile. Read-only, FREE. Requires your rs_live_* key (or wallet-JWT / MCP token); scoped to YOUR account only. Example
Create a one-tap Stripe Checkout link to add credit to YOUR balance — hand it to a human to open and pay. NO money moves here (it returns a URL; the balance is credited when the human pays). Use when
Search the full Relaystation tool catalog by keyword and get back the best matches. Use this first to find a tool, then `describe_tool` for its schema and `call_tool` to run it (or call a named hot to
Get one tool's full description and input schema by exact name (as returned by search_tools). FREE. Example: describe_tool {name:'pdf_merge'}
Run a tool found via search_tools by name, passing its arguments. Dispatches the safe/billable utility tools (the cputools catalog + free reads/quotes) through the identical auth + billing + validatio
Create a binding-by-goodwill agreement between agents/parties and get back a contractId + termsHash + per-signer read tokens. The contract IS a hash-chained, auto-witnessed record (terms = entry 1, co
Append your consent to a contract (one entry on its hash chain). FREE. Two forms, no cross-method satisfaction: a "wallet" signer supplies an EIP-712 ContractConsent signature over the contract's term
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: ask_operator
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
infer from the conversation. The operator gets a Telegram notification on tRecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_baton
A tool description tries to alter the model’s use of another tool.
rite later with append_to_baton. flags.hashChaining=true makes an append log taRecommendationDescriptions must describe only their own tool.
tool: balance
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
allet-JWT / MCP token); scoped to YOUR account only. Example: balanceRecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_topup_link
A tool description tries to alter the model’s use of another tool.
credit to YOUR balance — hand it to a human to open and pay. NO moneyRecommendationDescriptions must describe only their own tool.
tool: search_tools
A tool description tries to alter the model’s use of another tool.
d a tool, then `describe_tool` for its schema and `call_tool` to run it (or cRecommendationDescriptions must describe only their own tool.
tool: describe_tool
A tool description tries to alter the model’s use of another tool.
(as returned by search_tools). FREE. Example: describe_tool {name:'pdf_mergeRecommendationDescriptions must describe only their own tool.
tool: call_tool
A tool description tries to alter the model’s use of another tool.
on, mint_token, ask_operator) are NOT dispatchable here: call them directlyRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
gram/email/SMS (ask_operator), message agents, mint+read agent inboxes (messRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: ask_operator
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ask_operator"RecommendationScope tools to the minimum needed.
tool: message_agent
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "message_agent"RecommendationScope tools to the minimum needed.
tool: create_baton
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_baton"RecommendationScope tools to the minimum needed.
tool: append_to_baton
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "append_to_baton"RecommendationScope tools to the minimum needed.
tool: mint_token
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "mint_token"RecommendationScope tools to the minimum needed.
tool: balance
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "balance"RecommendationScope tools to the minimum needed.
tool: create_topup_link
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_topup_link"RecommendationScope tools to the minimum needed.
tool: search_tools
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "search_tools"RecommendationScope tools to the minimum needed.
tool: create_contract
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_contract"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.