Signo

fi.signoPublished by signo.fiOfficial publisherv1.0.1Updated Oct 24, 2026

AI agents that watch DeFi positions: read a wallet report, draft agents for the owner to sign.

VerifiedStreamable HTTPWeb executableFinanceSecurity & Monitoring

Overview

AI-generated overview

Signo's hosted MCP server lets an assistant read public wallet reports and draft DeFi watch agents that the wallet owner reviews and signs.

What you can do
Read a public onchain wallet report with a Signo Score and prioritized findings, without keys or sign-in (wallet_insights_report). Draft inactive Notify or Prepare agents from plain English, returning a review link for the owner to sign. Draft an inactive Execute permission on a Shield chain, capped and expiring, for the owner to authorize onchain. With a Signo account, list, read, pause, resume, edit and remove your own agents and read their history.
When to use it
Useful when someone wants an assistant to set up monitoring for DeFi positions such as Aave health factors, LP ranges, Pendle maturities or idle cash, or to get a quick read-only assessment of a public wallet before acting.
Requirements
A remote Streamable HTTP endpoint; nothing to install. The no-sign-in address needs no account. The account address requires signing in with a Signo account via OAuth and wallet sign-in. Agents need the owner to connect a wallet and link Telegram and sign on the review page.
Before you install
Draft tools create review links and inactive agents; nothing runs until the wallet owner signs. Execute permissions grant one action with the owner's funds within signed caps and can be revoked onchain, so review limits, token, expiry and lifetime cap carefully. The account endpoint exposes and can pause, edit or remove your agents. Wallet reports use public chain data.

Installation

In SourceWeft

  1. Open Signo in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/fi.signo%2Fsigno/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "signo": {
      "type": "http",
      "url": "https://app.signo.fi/api/mcp"
    }
  }
}

README

Signo MCP server

[Signo MCP connector] [smithery badge] [M8ven Score]

Signo gives your AI assistant tools to set up agents that watch DeFi positions and alert you on Telegram. An agent can watch an Aave health factor, an LP range, a Pendle maturity or idle cash, and prepare the next step for you to sign.

The assistant only drafts. The wallet owner reviews every draft and signs it in Signo. The assistant never gets wallet keys or spending rights.

This repository is the public listing for Signo's hosted MCP server: its registry entry, setup snippets and example prompts. The server runs at app.signo.fi. There is nothing to install or build.

Addresses

AddressSign-inTools
https://app.signo.fi/api/mcpNone3 tools: read a public wallet report, draft an agent, draft an Execute permission
https://app.signo.fi/api/mcp/accountYour Signo account (OAuth, wallet sign-in)The same 3, plus 6 to list, read, pause, resume, edit and remove your own agents

Both speak MCP over Streamable HTTP. Official MCP Registry name: fi.signo/signo.

Add it

Claude Code, no sign-in:

bash
claude mcp add --transport http signo https://app.signo.fi/api/mcp

Cursor, in .cursor/mcp.json:

json
{  "mcpServers": {    "signo": { "url": "https://app.signo.fi/api/mcp" }  }}

Claude (claude.ai, web or desktop), with your account:

  1. Open Settings, then Connectors, and click Add custom connector.
  2. Name it Signo and enter https://app.signo.fi/api/mcp/account.
  3. Click Connect, sign in with your wallet on the Signo page, and click Allow.

ChatGPT (developer mode), with your account:

  1. In Settings, open Apps & Connectors, then Advanced settings, and turn on Developer mode.
  2. Create an app named Signo with https://app.signo.fi/api/mcp/account and OAuth.
  3. Sign in with your wallet on the Signo page and click Allow.

More setup detail: docs.signo.fi/for-assistants.

Tools

No sign-in:

ToolWhat it does
wallet_insights_reportReads a public report on any wallet, with the agents it suggests. Read-only.
signo_draft_agentDrafts a Notify or Prepare agent from plain English. Returns a review link for the owner.
signo_draft_permissionDrafts an inactive Execute permission on X Layer or Arbitrum. The owner authorizes it onchain. Execute is in early access; a wallet without access gets a Prepare draft instead.

With your Signo account, also:

ToolWhat it does
signo_account_agentsLists the agents on your account.
signo_account_agentReads one agent's setup and its last check.
signo_account_agent_historyReads its notifications and Execute runs.
signo_account_agent_statusPauses or resumes it.
signo_account_agent_updateEdits supported fields on Notify and Prepare agents.
signo_account_agent_removeRemoves it and keeps its history.

How a draft becomes an agent

  1. The assistant calls a draft tool and gets a private review link.
  2. The wallet owner opens the link, connects the wallet and links Telegram.
  3. The owner signs once. Only then does the agent run.

An Execute permission sets one action, one token, a limit per firing, a lifetime limit and an expiry. The Signo Shield contract checks every firing against those limits. The owner can revoke it onchain at any time.

Example prompts

See examples/prompts.md.

Links

License

The files in this repository are under the MIT License. See LICENSE.

Source: README.md at commit b97a4b7

Tools

3

signo_draft_agent

Draft a Signo agent (Notify or Prepare) for the owner to claim

Draft a complete inactive Notify or Prepare agent, without an API key. Name the owner wallet when you know it; omit it and the first wallet to sign on the review page owns the agent. It can watch anything the app can: a price threshold or percent move, portfolio movement, a lending health factor (Aave, Spark, Compound V3, Morpho), the owner's own DeFi positions (PTs, LPs, supplied assets, claimables, APY or value changes, days to expiry), Pendle loops, a daily market brief, a recurring schedule (daily, weekly or monthly at a set time, or hourly checks) or any plain-English condition the compiler accepts. Execute is a separate permission flow with its own supported conditions and typed on-chain triggers; Execute is not available for the app's Portfolio move trigger, boxed Pendle PT loops are notify-only, and recurring schedules are not Execute triggers today. Returns a private review_url plus summary, cadence (hourly or daily checks), autonomy, action and expires_at in unix milliseconds. The owner opens the link, connects that wallet, links Telegram and signs once to create the agent. Set autonomy to prepare for an action request; otherwise it is refused as autonomy_mismatch, not silently downgraded. Prepare builds an unsigned plan on each fire; it never spends automatically. No clarification round trip: an ambiguous or unwatchable request is a 422 with the reason, so rephrase and call again. Keyless has no agent-status read yet: the owner sees fires on the Agents page and on Telegram. Automatic execution is the separate signo_draft_permission tool.

Parameterswalletrequestrequiredautonomy

signo_draft_permission

Draft a Signo Shield permission (Execute) for the owner to sign

Draft an Execute agent on a deployed Shield chain: when something happens on the owner's wallet, do one action with its funds, inside caps the owner signs on chain (the Shield contract). Inactive until the owner signs on the review link it returns (review_url; also proposal_id, summary, limits, fee_bps, expires_at). No API key. New Execute setup is in early access: a wallet without access no longer gets 403 execute_team_only: no proposal is stored, and the response is a Prepare agent draft for the same trigger and action instead (status 'draft', fallback.from 'execute', its own review_url). The owner activates it and signs each plan, and can join the Execute waitlist in the Signo app. Collect: wallet; trigger; action; cap_per (most per execution); budget (lifetime, before fees; the fee comes on top); expiry_days optional, default 30. The wallet need not hold the budget yet. Trigger: { kind: "condition", request } for a supported plain-English Execute condition, e.g. "when XETH drops 10% in 24 hours" (what the Shield cannot read, the hourly check decides); or health_factor, token_balance or price, re-checked on chain, e.g. { kind: "price", asset: "XETH", comparator: "<", value: 3000 }. Execute is not available for the app's Portfolio move trigger; boxed Pendle PT loops are notify-only today, and a recurring schedule is not an Execute trigger. Action: transfer, swap (OKX DEX; one of min_out or max_slippage_bps), vault (ERC-4626), supply (Aave), repay_from_wallet, repay_from_collateral. Assets by symbol or address. Fee 10 bps per firing. Enforced on chain: the Shield re-checks caps, expiry and readable triggers each firing and pulls funds via the owner's allowance; the executor key is held in Google Cloud KMS and usable only by Signo's production service. Checked hourly; one successful execution completes a trigger by default, and public drafts do not opt into repay-from-collateral continuation. The signing service allows at most two attempts for one permission in

Parametersactionrequiredbudgetrequiredwalletrequiredcap_perrequiredtriggerrequiredchain_idrequiredexpiry_daysschema_versionrequired

wallet_insights_report

Signo: wallet insights report

Analyze any public onchain wallet and return its Signo Score plus prioritized findings. Covers yield left on the table, leverage safety, LP health, idle capital, dust and unclaimed rewards. Read-only: it inspects public chain data and never moves funds, needs no keys, and requires no connected session — so it works on any address you can name, not just one the caller controls. Returns signoScore (0-100, the Signo Score: how well the wallet's capital is managed, from idle cash, yield against the cash benchmark, unclaimed rewards, the leverage guard and dust; it is not a safety or liquidation-risk score). This public tool cannot read the owner's private Agents, so watch coverage is not_applicable with 'Agent coverage isn't shown here' and signoScore omits that category; the signed-in owner's app score can differ. riskTolerance, walletAge, holdings (every chain's tokens, DeFi positions and loans with USD values, largest first, so you can structure your own view), and a categories array where each entry carries state, headline, detail and a suggested next step. Findings that call for an agent carry agentSuggestion, and the report carries suggestedAgents plus draftWith: exact request and autonomy arguments for the sibling signo_draft_agent tool on this host, so you can draft the agent for the wallet owner to activate. Free.

Parametersaddressrequirednarrative

Version history

2
  1. v1.0.1LatestOct 16, 2026
  2. v1.0.0Oct 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts