Skip to main content
Glama

Prepare a REGEN bridge transaction (non-custodial)

prepare_bridge
Read-onlyIdempotent

Move REGEN between the Regen chain, Osmosis, Arbitrum and Base in ONE transaction the caller signs with their own wallet. Returns a live quote and the exact unsigned transaction; Skip Go's relayers carry every hop after the broadcast: no confirm step, nothing held by this server, free. Five routes: regen→arbitrum, regen→base and base→regen (axlREGEN through Axelar), plus regen→osmosis and osmosis→regen (a plain ICS-20 transfer over regen-1 channel-1 and osmosis-1 channel-8). This tool prepares that ICS-20 leg itself: zero toll, amount out equals amount in, one signed message, timeouts derived live by Skip, and no minimum send; on those two legs destination may be omitted, and the sender's own account re-encoded under the destination prefix is used (same key, same 20 bytes, no new wallet). Skip does now return a one-transaction route from Osmosis to Base, but it is a CosmWasm contract call rather than a plain ICS-20 transfer, and this tool prepares only ICS-20 transfers and Axelar sends, so it is not offered here; from Osmosis, route home first (osmosis→regen), then regen→base or regen→arbitrum from the regen1 address. Base USDC to REGEN and the reverse take two signed transactions and are not offered here either. Outbound sends from the Regen chain to Arbitrum or Base pay Axelar's flat per-transfer toll, which Axelar prices in dollars (about $0.19 to $0.23 measured across 2026-09-05 to 2026-09-08) and so floats in REGEN terms: measured between 94 and 175 REGEN across those days, on a transfer of any size, moving with both the REGEN price and the shape of the route Skip picks. It is quoted LIVE at call time and returned as quote.toll_regen. The response is authoritative; the figures in this text are approximate and there is no stable number to publish. On those Axelar routes send at least twelve times the live toll in one transfer (returned as quote.min_send_regen, which is null on the Osmosis legs because they have no minimum) and batch rather than dribble; a smaller send is refused with the live toll named. base→regen carries no REGEN toll: the prepared EVM transaction carries a small native ETH value instead, Axelar's fee as Skip quotes it (about $0.11 measured 2026-09-08, returned as sign_this.value and refused above $0.50), after one exact ERC-20 approval. Measured landing times with one key, every landing read from the destination chain on 2026-09-08: regen→osmosis under a minute, regen→base about 66 seconds, base→regen about 30 minutes because Axelar waits on Base finality before it approves an EVM to Cosmos call. After the broadcast, call bridge_status with the source chain and the transaction hash to follow it; a round trip through Base and back loses money at every size this tool prepares (the flat toll never crosses the small price spread), so move REGEN to where it is needed, never to trade the gap.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
amountYesAmount in whole REGEN (e.g. "5000"). Same 6-decimal unit on every chain.
senderYesThe caller's OWN address on from_chain (regen1… for regen, osmo1… for osmosis, 0x… for base and arbitrum): the wallet that will sign.
to_chainYesChain the REGEN should end up on.
from_chainYesChain the REGEN is on now.
destinationNoThe caller's OWN address on to_chain that receives the funds. Required on the Arbitrum and Base routes, where no address can be derived from the sender's. Optional on regen→osmosis and osmosis→regen: when omitted, the sender's own account re-encoded under the destination prefix is used (same key, same 20 bytes, no new wallet).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okNo
toolNo
fundedNo
payUsdNo
workIdNo
claimIdNo
claimableNo
next_callNo
proofRuleNo
fulfillableByNo
definitionOfDoneNo
needs_from_callerNo
notClaimableReasonNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / destination / description
      Previous value: -"The caller's OWN address on to_chain that receives the funds."New value: +"The caller's OWN address on to_chain that receives the funds. Required on the Arbitrum and Base routes, where no address can be derived from the sender's. Optional on regen→osmosis and osmosis→regen: when omitted, the sender's own account re-encoded under the destination prefix is used (same key, same 20 bytes, no new wallet)."
    • changedInput schema / properties / from_chain / enum
      Previous value: -[
      -  "regen",
      -  "base",
      -  "arbitrum"
      -]New value: +[
      +  "regen",
      +  "base",
      +  "arbitrum",
      +  "osmosis"
      +]
    • changedInput schema / properties / sender / description
      Previous value: -"The caller's OWN address on from_chain (regen1… for regen, 0x… for base) — the wallet that will sign."New value: +"The caller's OWN address on from_chain (regen1… for regen, osmo1… for osmosis, 0x… for base and arbitrum): the wallet that will sign."
    • changedInput schema / properties / to_chain / enum
      Previous value: -[
      -  "regen",
      -  "base",
      -  "arbitrum"
      -]New value: +[
      +  "regen",
      +  "base",
      +  "arbitrum",
      +  "osmosis"
      +]
    • changedInput schema / required
      Previous value: -[
      -  "from_chain",
      -  "to_chain",
      -  "amount",
      -  "sender",
      -  "destination"
      -]New value: +[
      +  "from_chain",
      +  "to_chain",
      +  "amount",
      +  "sender"
      +]
  2. Changed2 schema fields changed
    • addedOutput schema / properties / claimable
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / notClaimableReason
      Added value: +{
      +  "type": "string"
      +}
  3. Added

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Even though annotations already signal readOnly, idempotent, and non-destructive behavior, the description goes far beyond them: it discloses live quoting, relayers carrying every hop, no confirm step, no server custody, free service, fee ranges in REGEN and ETH, refusal thresholds, landing times, and the warning that round trips through Base lose money. Nothing contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is thorough and front-loaded with the core operation, but it is an extremely dense single block of prose with time-stamped measurements ('about $0.19 to $0.23 measured across 2026-09-05 to 2026-09-08') and many multi-clause sentences. Every fact is purposeful, but the density and lack of structural separation prevent it from being truly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex financial tool, the description is complete: it covers all five routes, fees, minimums, timing, exclusions, follow-up via bridge_status, and even names relevant output fields like quote.toll_regen and sign_this.value. Since an output schema exists, the description does not need to list return values, and nothing needed for correct invocation appears missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already has 100% parameter coverage, so the baseline is 3. The description adds route-specific meaning beyond the schema: destination can be omitted on Osmosis legs and the sender's address is re-encoded under the destination prefix (same key, same 20 bytes), minimum-send constraints affect the amount parameter, and the live toll determines whether a transfer is refused. This is meaningful added semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Move REGEN between the Regen chain, Osmosis, Arbitrum and Base in ONE transaction the caller signs with their own wallet. Returns a live quote and the exact unsigned transaction.' This establishes the non-custodial, prepare-only nature and clearly differentiates the tool from bridge_status and submit_* siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use the tool, when not to use it (Osmosis→Base CosmWasm route and Base USDC routes are not offered), gives an alternative path ('route home first (osmosis→regen), then regen→base or regen→arbitrum'), and tells the agent to call bridge_status after broadcast. It also provides minimum-send and batching guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources