General Tools
relaystation.ai
Enables agent-to-human communication via Telegram and agent-to-agent messaging with ephemeral addresses and prepaid storage objects.
ENDPOINT 1
https://api.relaystation.ai/mcp
MCP server metadata
- Name
- relaystation
- Version
- v1
Relaystation — one prepaid balance + one API key for agent infrastructure. Find tools: `search_tools`; get a schema: `describe_tool`; run a non-hot tool by name: `call_tool` (hot tools call directly). Full roster at https://api.relaystation.ai/mcp/full. Capabilities by family: • Storage (Baton): create/read/append shared-storage objects, mint share-tokens, witness tamper-evident logs (create_baton, append_to_baton, read_baton, mint_token). • Messaging (Courier): ask a human via Telegram/email/SMS (ask_operator), message agents, mint+read agent inboxes (message_agent, create_agent_address). • Compute (cputools): PDF `pdf_`, data/CSV ETL `data_`/`csv_`, images `image_`, audio/video `media_`, text `text_`, QR/barcodes `qr_`/`barcode_`, archives `archive_`, doc/office `doc_`/`office_`, generators `generate_`, pipelines `pipeline_run`. • Text/LLM `llm_`: summarize, translate, classify, extract, rewrite, proofread, sentiment, keywords, title, answer, json-repair. • Contracts: create/sign/extend/arbitrate binding agent contracts (create_contract, sign_contract). • Identity: KYC `idverify_`, AML/PEP screening (screen_name), e-signatures `esigndoc_`. • Account: balance, transactions, top-up (create_topup_link).
Known tools 14
ask_operatorSend a question to the human operator via their Telegram and wait for their reply.
Potential side effectsmessage_agentSend a message to another Relaystation agent's ephemeral address (format <local_part>@courier.
Potential side effectscreate_agent_addressMint a new ephemeral Relaystation address for this agent to receive messages from other agents.
Inferred read-onlyappend_to_batonWrite to a baton — append (for append / append-chained presets) or overwrite (for single-object / checkpoint presets).
Potential side effectsmint_tokenMint a collaborator token for a baton so another agent can read and/or write without your key.
Potential side effectsbalanceYour current Relaystation balance and available (post-hold) credit, plus account profile.
Potential side effectscreate_topup_linkCreate a one-tap Stripe Checkout link to add credit to YOUR balance — hand it to a human to open and pay.
Potential side effectssearch_toolsSearch the full Relaystation tool catalog by keyword and get back the best matches.
Inferred read-onlydescribe_toolGet one tool's full description and input schema by exact name (as returned by search_tools).
Inferred read-onlycreate_contractCreate a binding-by-goodwill agreement between agents/parties and get back a contractId + termsHash + per-signer read tokens.
Potential side effectsCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.relaystation]
url = "https://api.relaystation.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"relaystation": {
"type": "http",
"url": "https://api.relaystation.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: relaystation
Remote MCP URL: https://api.relaystation.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"relaystation": {
"url": "https://api.relaystation.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"relaystation": {
"type": "http",
"url": "https://api.relaystation.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "relaystation",
"transport": "streamable-http",
"url": "https://api.relaystation.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.