Model Context Protocol (MCP) server for freee API integration
Odyssey Loopr is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Quote, build and simulate leveraged DeFi yield positions on Odyssey Loopr.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http odyssey-loopr-mcp https://app.odyssey.finance/api/mcp
# 2 — ask your agent for something these tools do
# list_strategies, get_strategy, get_positions and 14 more
Odyssey Loopr costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http odyssey-loopr-mcp https://app.odyssey.finance/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List Loopr leveraged strategies with APY, leverage bounds, deposit/borrow tokens and TVL. Filter by chain, deposit asset or protocol.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| assets | array | no | Deposit token addresses |
| chainIds | array | no | — |
| includeDisabled | boolean | no | Include delisted strategies (default false) |
| protocols | array | no | Protocol families, e.g. 'aave', 'morpho' |
Get one strategy. Pass depositToken/borrowToken when several strategies share a strategyId on the same chain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| borrowToken | string | no | — |
| chainId | integer | yes | EVM chain id |
| depositToken | string | no | — |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
List an owner EOA's Loopr positions with health, leverage and PnL. Requires chainId or chainIds. Pass positionAddress (with chainId, not chainIds) to fetch a single position: it returns { position, errors, catalogUnavailable }, and a null position with errors rows means the chain could not be read, not that the position does not exist.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | no | EVM chain id |
| chainIds | array | no | — |
| owner | string | yes | Owner EOA |
| positionAddress | string | no | — |
Derive the smart contract account (SCA) that holds Loopr positions for an EOA. Deterministic; the same on every chain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| eoa | string | yes | — |
Quote opening a leveraged position: expected collateral, debt, health factor and liquidation price. Returns a quote envelope; expiresAt is unix ms and quotes expire after 180 seconds. Amounts are base-unit integer strings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | string | yes | Collateral amount in base units |
| borrowToken | string | no | Disambiguates strategies that share strategyId and collateral |
| chainId | integer | yes | EVM chain id |
| collateralToken | string | yes | — |
| leverage | number | yes | Target leverage as a plain number between 1.01 and 100: 3 means 3x (not 1e18 fixed-point). An open must borrow, so 1 is not accepted; to add collateral without borrowing, adjust an existing position |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
Quote adding collateral ('push', requires leverage) or withdrawing it ('pull'). Returns a quote envelope; expiresAt is unix ms and quotes expire after 180 seconds. Amounts are base-unit integer strings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| amount | string | yes | Collateral to add or withdraw, in base units |
| direction | string | yes | — |
| leverage | number | no | Target leverage as a plain number between 1 and 100: 3 means 3x (not 1e18 fixed-point) |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
Quote borrowing more against a position. Returns a quote envelope; expiresAt is unix ms and quotes expire after 180 seconds. Amounts are base-unit integer strings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| borrowAmount | string | yes | — |
| marketId | string | no | Morpho market id (optional) |
Quote repaying debt. 'auto' repays from collateral via a flash-loan swap and requires slippage; 'manual' repays from the wallet. Returns a quote envelope; expiresAt is unix ms and quotes expire after 180 seconds. Amounts are base-unit integer strings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| mode | string | yes | — |
| repayAmount | string | yes | — |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
| withdrawAmount | string | no | 'auto' only |
Quote claiming rewards. 'send' pays them to the owner; 'compound' swaps them into the position and requires slippage. The returned rewards feed build_claim. Returns a quote envelope; expiresAt is unix ms and quotes expire after 180 seconds. Amounts are base-unit integer strings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| mode | string | yes | — |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
Quote closing a position in full. Returns a quote envelope; expiresAt is unix ms and quotes expire after 180 seconds. Amounts are base-unit integer strings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
Build the steps that open a leveraged position. Returns UNSIGNED transaction steps for the owner to sign in order; this server never holds keys or sends transactions. The build expires after 180 seconds (expiresAt, unix ms): build immediately before signing, not as a plan for later. Builds are single-use: rebuilding an open predicts a different position address, so never replay one. A successful
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | string | yes | Collateral (or tokenIn) amount in base units |
| approvalMode | string | no | ERC-20 approval size. 'exact' (default) approves only this amount |
| borrowToken | string | yes | — |
| chainId | integer | yes | EVM chain id |
| collateralToken | string | yes | — |
| forceSwapper | boolean | no | Retry only: route the swap through the swapper instead of the routing engine. Set it when simulate reports a build as failing, then rebuild. |
| leverage | number | yes | Target leverage as a plain number between 1.01 and 100: 3 means 3x (not 1e18 fixed-point). An open must borrow, so 1 is not accepted; to add collateral without borrowing, adjust an existing position |
| maxPriceImpact | number | no | Zap-in only: decimal price-impact ceiling (0.1 = 10%) |
| owner | string | yes | EOA that owns the position and signs the steps. The smart account is derived from it server-side. |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| tokenIn | string | no | — |
| tokenInSwapper | string | no | — |
Build the steps that add collateral ('push': requires collateralToken, amount, borrowToken, leverage) or withdraw it ('pull': requires token, tokenOut, and exactly one of withdrawAmount or withdrawAll). Fields of the other direction are refused, not ignored. Returns UNSIGNED transaction steps for the owner to sign in order; this server never holds keys or sends transactions. The build expires afte
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| amount | string | no | 'push' only: amount to add |
| approvalMode | string | no | 'push' only |
| borrowToken | string | no | 'push' only |
| collateralToken | string | no | 'push' only |
| direction | string | yes | — |
| forceSwapper | boolean | no | 'push' only. Retry only: route the swap through the swapper instead of the routing engine. Set it when simulate reports a build as failing, then rebuild. |
| leverage | number | no | Target leverage as a plain number between 1 and 100: 3 means 3x (not 1e18 fixed-point) |
| maxPriceImpact | number | no | 'push' zap-in only: decimal price-impact ceiling |
| owner | string | yes | EOA that owns the position and signs the steps. The smart account is derived from it server-side. |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
| token | string | no | 'pull': position collateral token |
| tokenIn | string | no | 'push' only |
| tokenInSwapper | string | no | 'push' only |
| tokenOut | string | no | 'pull': token to receive |
| withdrawAll | boolean | no | 'pull' only |
| withdrawAmount | string | no | 'pull' only: collateral to withdraw, in base units |
Build the steps that borrow more against a position. Returns UNSIGNED transaction steps for the owner to sign in order; this server never holds keys or sends transactions. The build expires after 180 seconds (expiresAt, unix ms): build immediately before signing, not as a plan for later. Builds are single-use: rebuilding an open predicts a different position address, so never replay one. A succe
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| borrowAmount | string | yes | — |
| marketId | string | no | — |
| owner | string | yes | EOA that owns the position and signs the steps. The smart account is derived from it server-side. |
Build the steps that repay debt. 'auto' requires slippage; 'manual' repays from the owner's wallet. Returns UNSIGNED transaction steps for the owner to sign in order; this server never holds keys or sends transactions. The build expires after 180 seconds (expiresAt, unix ms): build immediately before signing, not as a plan for later. Builds are single-use: rebuilding an open predicts a different
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| approvalMode | string | no | 'manual' only |
| forceSwapper | boolean | no | 'auto' only. Retry only: route the swap through the swapper instead of the routing engine. Set it when simulate reports a build as failing, then rebuild. |
| mode | string | yes | — |
| owner | string | yes | EOA that owns the position and signs the steps. The smart account is derived from it server-side. |
| repayAmount | string | yes | — |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
| withdrawAmount | string | no | 'auto' only |
Build the steps that claim rewards. Pass rewards exactly as quote_claim returned them. 'compound' requires slippage. Returns UNSIGNED transaction steps for the owner to sign in order; this server never holds keys or sends transactions. The build expires after 180 seconds (expiresAt, unix ms): build immediately before signing, not as a plan for later. Builds are single-use: rebuilding an open p
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| mode | string | yes | — |
| owner | string | yes | EOA that owns the position and signs the steps. The smart account is derived from it server-side. |
| rewards | array | yes | — |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
Build the steps that close a position in full. Returns UNSIGNED transaction steps for the owner to sign in order; this server never holds keys or sends transactions. The build expires after 180 seconds (expiresAt, unix ms): build immediately before signing, not as a plan for later. Builds are single-use: rebuilding an open predicts a different position address, so never replay one. A successful
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id |
| positionAddress | string | yes | Position (vault) address |
| strategyId | integer | yes | Strategy id from list_strategies (strategyId) |
| forceSwapper | boolean | no | Retry only: route the swap through the swapper instead of the routing engine. Set it when simulate reports a build as failing, then rebuild. |
| owner | string | yes | EOA that owns the position and signs the steps. The smart account is derived from it server-side. |
| receiveToken | string | no | Token to receive (defaults to the deposit token) |
| slippage | number | no | Slippage tolerance as a decimal: 0.005 means 0.5% (not 1e18 fixed-point) |
Simulate built steps on a fork (Tenderly) from the owner's address before anyone signs. Pass steps and expiresAt exactly as a build_* tool returned them. Check ok; on failure the failing step carries the revert reason; never ask anyone to sign a failing build. A swap-route failure can be retried by rebuilding with forceSwapper: true (build_open, build_adjust push, build_repay auto, build_c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| expiresAt | integer | yes | The build’s expiresAt (unix ms) |
| from | string | yes | Owner EOA that will sign the steps |
| share | string | no | — |
| steps | array | yes | — |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Odyssey Loopr or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_strategies | no tags | |
| get_strategy | no tags | |
| get_positions | untrusted-input | untrusted-input: keyword "fetch" |
| get_sca_account | no tags | |
| quote_open | no tags | |
| quote_adjust | no tags | |
| quote_borrow | no tags | |
| quote_repay | no tags | |
| quote_claim | no tags | |
| quote_close | no tags | |
| build_open | no tags | |
| build_adjust | no tags | |
| build_borrow | no tags | |
| build_repay | no tags | |
| build_claim | no tags | |
| build_close | no tags | |
| simulate | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.2.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Odyssey Loopr can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.