On-chain DEX aggregator quotes, phantom-liquidity scanning, and live proof-of-solvency across Base, Ethereum, Optimism, Arbitrum, and Robinhood Chain. Keyless, no auth.
Scored across 4 tools
prepare_quote and decode_quote form an explicit encode/decode pair, and get_abi and get_deployments are clearly distinct lookups; the descriptions even spell out the pipeline between them. The only wobble is prepare_quote, whose name suggests it produces a quote when it actually builds an eth_call, but the description removes any real doubt.
All four tools use a clean snake_case verb_noun pattern (prepare_quote, decode_quote, get_abi, get_deployments), with get_* for pure lookups and prepare/decode for the quote pipeline. Fully predictable.
Four tools is on the lean side but each earns its place in a deliberately narrow, no-RPC-by-design surface. Nothing is redundant, though the set leaves little room for adjacent helpers (e.g. token metadata) that a user might expect.
The core lifecycle is closed-loop: discover addresses (get_deployments), encode custom calls (get_abi), build the quote call (prepare_quote), and interpret the result (decode_quote). Minor gaps only—no explicit tool for fee/version or token lookup beyond what decode_quote narrates—which agents can work around.
Decode the eth_call result YOUR node returned for a prepare_quote call: net output after the 0.28% fee, the minimum the Router enforces on-chain, price impact, the Phoenix Check verdict (ok / caution / danger / blocked — fails closed) and, with a recipient, verified unsigned calldata. Pure computation.
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes | the 0x hex result of the eth_call on your node | |
| request | Yes | the `request` object prepare_quote returned, verbatim |
| Name | Required | Description |
|---|---|---|
| ok | Yes | false: see code, error |
| tx | No | |
| code | No | |
| meta | No | |
| mode | No | |
| entry | No | |
| error | No | |
| exact | No | |
| quote | No | |
| route | No | |
| checks | No | |
| minOut | No | |
| chainId | No | |
| tokenIn | No | |
| txError | No | |
| amountIn | No | |
| approval | No | |
| deadline | No | |
| tokenOut | No | |
| amountOut | No | |
| encodedBy | No | |
| executeWith | No | |
| unwrapAfter | No | |
| wrapRequired | No | |
| grossAmountOut | No | |
| protocolVersion | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false; the description corroborates with 'Pure computation' and adds genuinely new behavior: the Phoenix Check verdict is a four-value enum that 'fails closed', and calldata is only verified/unsigned when a recipient is present. That is useful context beyond the annotation set, though it says nothing about failure modes for malformed input.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that opens with the core action and only then enumerates the returned fields. It is dense and somewhat run-on, but every clause (fee, minimum, price impact, verdict, calldata) carries information an agent would otherwise have to infer.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so the description need not explain return values, yet it still telegraphs them and, more importantly, pins down the upstream dependency chain (prepare_quote request plus an eth_call result from the caller's own node). Given annotations and full schema coverage, nothing essential is missing, only edge-case guidance for invalid inputs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters (result, request) are already documented in the schema, including that `request` must be the object prepare_quote returned verbatim. The description reinforces the provenance of both inputs but adds no format, encoding, or size detail beyond the schema, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (decode) and resource (the eth_call result for a prepare_quote call), and enumerates exactly what it produces: net output after fee, Router-enforced minimum, price impact, Phoenix Check verdict, verified calldata. This clearly distinguishes it from get_abi, get_deployments and prepare_quote, which it explicitly references as the upstream step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description makes the workflow explicit: it operates on the eth_call result YOUR node returned for a prepare_quote call, so the agent knows it must first have a prepare_quote `request` and a raw node result. It does not state exclusions or what to do instead when those inputs are missing, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The JSON ABI of one BlazePhoenix contract, generated from the Solidity sources, with the source revision it was built from. Use it to encode your own calls to the addresses get_deployments returns, or pass errors to decode a revert reason from a failed swap or quote. Returns { contract, revision, abi }; an unknown name returns ok:false with the accepted list. Pure lookup, no RPC.
| Name | Required | Description | Default |
|---|---|---|---|
| contract | Yes | quoter (quotes and previews) | router (swap entry point) | solver | hub | core | errors (the protocol custom-error set, for decoding reverts) |
| Name | Required | Description |
|---|---|---|
| ok | Yes | false: see code, error |
| abi | No | |
| code | No | |
| error | No | |
| contract | No | |
| revision | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint/idempotentHint/openWorldHint, so the safety profile is covered. The description adds useful behavior beyond that: generated-from-Solidity provenance, source revision in the response, the ok:false + accepted-list failure mode for unknown names, and 'Pure lookup, no RPC' (relevant given openWorldHint=false).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences: what it returns and its provenance, how to use it (with the `errors` case), and the return shape plus failure mode. Front-loaded and no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite an output schema existing, the description still gives the return shape ({ contract, revision, abi }) and the error envelope, plus the special-case behavior of `errors`. Combined with annotations and full schema coverage, an agent has everything needed to call this correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the enum already lists meanings, so baseline applies. The description adds semantic value by explaining the intended use of the `errors` value (decode reverts) and tying `contract` selection to addresses from get_deployments, which is more than the schema conveys.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource (retrieve the JSON ABI of a BlazePhoenix contract, generated from Solidity sources with its source revision). This is clearly different from the siblings get_deployments (addresses), prepare_quote/decode_quote (quote operations), and names an output shape.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use it: to encode your own calls to addresses from get_deployments, or pass `errors` to decode revert reasons from a failed swap/quote. It names the routing dependency (get_deployments) and the special-case enum value that changes the tool's purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The versioned BlazePhoenix deployment registry: Core, Hub, Solver, Quoter and Router addresses per chain and protocol version (1.0.0 live; 2.0.0 the final generation), and which version each chain runs now.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| ok | Yes | false: see code, error |
| active | No | |
| schema | No | |
| versions | No | |
| updatedAt | No | |
| localServer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds domain-level context the annotations cannot (1.0.0 is live, 2.0.0 is the final generation, per-chain version resolution), which is genuinely useful, but it says nothing about response shape, caching or freshness beyond the version labels.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that packs the resource, its contents and the versioning semantics without filler. The parenthetical about versions is dense but earns its place; only minor readability cost from the run-on structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no parameters and an output schema that documents return values, the description's job is small and it largely does it: it explains what the registry contains and how versions map to chains. The only missing piece is any indication of when an agent should reach for this tool rather than the quoting/ABI siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so the baseline is 4; there is no parameter surface for the description to clarify or omit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific resource (the BlazePhoenix deployment registry) and enumerates its contents (Core, Hub, Solver, Quoter, Router addresses per chain and protocol version), so an agent knows exactly what it retrieves. It does not differentiate itself from siblings decode_quote/get_abi/prepare_quote, though those are functionally distant, so the cost is small.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: an agent can infer this is the tool to call when it needs contract addresses for a chain/version, but there is no explicit when-to-use, no when-not-to-use, and no named alternative. Adequate but with a clear gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Prepare an on-chain BlazePhoenix quote to run on YOUR OWN RPC. Returns the exact eth_call (Quoter address + calldata, as a ready JSON-RPC request and a curl line) plus a request object. Run the call on your node, then pass request and the result hex to decode_quote. This server performs no RPC.
| Name | Required | Description | Default |
|---|---|---|---|
| in | Yes | input token — 0x address, or ETH / WETH / USDC / BZPX | |
| out | Yes | output token — 0x address, or ETH / WETH / USDC / BZPX | |
| chain | Yes | base | eth | optimism | arbitrum | robinhood (or a chain id) | |
| exact | No | true → previewPlanExact: every leg dry-run on its pool in this block; with recipient + userMinOut also calldata (exact mode applies a safety margin: userMinOut at or under exactOut less 50 bps). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that | |
| version | No | protocol version: latest (default) | 1 | 2 | 2.0.0 | |
| amountIn | Yes | input amount in base units (wei-style integer string) | |
| recipient | No | optional 0x address; with it, decode_quote returns signable calldata | |
| userMinOut | No | minimum output, base units, from a price you trust; required for calldata, which enforces exactly this value | |
| deadlineSec | No | deadline horizon in seconds, 10–3600 (default 120) | |
| slippageBps | No | 0–5000 (default 50); how far under the quoted net output userMinOut may sit |
| Name | Required | Description |
|---|---|---|
| ok | Yes | false: see code, error |
| call | No | |
| code | No | |
| curl | No | |
| mode | No | |
| note | No | |
| error | No | |
| decode | No | |
| chainId | No | |
| request | No | |
| contracts | No | |
| rpcRequest | No | |
| protocolVersion | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnly, idempotent, openWorld=false), and the description adds concrete behavior: it returns a ready JSON-RPC request plus curl line and a `request` object, and performs no RPC itself. That workflow contract is context the annotations cannot supply.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with the core action, followed by what is returned and the next step. No filler, nothing redundant with structured fields.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a stateless quote-preparation tool with an output schema and rich annotations, the description covers the contract (what is returned, no RPC performed, handoff to decode_quote) sufficiently. An agent has everything needed to invoke and chain it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter (including exact-mode margins, deadlineSec range, slippageBps bounds) is already documented in the schema. The description adds workflow context but no per-parameter detail, so the baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Prepare an on-chain BlazePhoenix quote') and immediately scopes it ('to run on YOUR OWN RPC'), which distinguishes it from the decode step among siblings. An agent can tell what this produces without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly chains the workflow: run the returned eth_call on your node, then pass `request` plus the result hex to decode_quote. It also draws the boundary ('This server performs no RPC'), so the agent knows what happens here vs. elsewhere.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
prepare_quote3 fields changedInput schema / properties / exact / descriptionPrevious value: -"true → previewPlanExact: every leg dry-run on its pool in this block (no calldata). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that"New value: +"true → previewPlanExact: every leg dry-run on its pool in this block; with recipient + userMinOut also calldata (exact mode applies a safety margin: userMinOut at or under exactOut less 50 bps). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that"Input schema / properties / slippageBps / descriptionPrevious value: -"0–5000 (default 50); never below the on-chain floor"New value: +"0–5000 (default 50); how far under the quoted net output userMinOut may sit"Input schema / properties / userMinOut / descriptionPrevious value: -"optional explicit minimum output, base units"New value: +"minimum output, base units, from a price you trust; required for calldata, which enforces exactly this value"prepare_quote3 fields changedInput schema / properties / exact / descriptionPrevious value: -"true → previewPlanExact: every leg dry-run on its pool in this block; with recipient + userMinOut also calldata (exact mode applies a safety margin: userMinOut at or under exactOut less 50 bps). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that"New value: +"true → previewPlanExact: every leg dry-run on its pool in this block (no calldata). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that"Input schema / properties / slippageBps / descriptionPrevious value: -"0–5000 (default 50); how far under the quoted net output userMinOut may sit"New value: +"0–5000 (default 50); never below the on-chain floor"Input schema / properties / userMinOut / descriptionPrevious value: -"minimum output, base units, from a price you trust; required for calldata, which enforces exactly this value"New value: +"optional explicit minimum output, base units"prepare_quote3 fields changedInput schema / properties / exact / descriptionPrevious value: -"true → previewPlanExact: every leg dry-run on its pool in this block (no calldata). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that"New value: +"true → previewPlanExact: every leg dry-run on its pool in this block; with recipient + userMinOut also calldata (exact mode applies a safety margin: userMinOut at or under exactOut less 50 bps). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that"Input schema / properties / slippageBps / descriptionPrevious value: -"0–5000 (default 50); never below the on-chain floor"New value: +"0–5000 (default 50); how far under the quoted net output userMinOut may sit"Input schema / properties / userMinOut / descriptionPrevious value: -"optional explicit minimum output, base units"New value: +"minimum output, base units, from a price you trust; required for calldata, which enforces exactly this value"decode_quote1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "amountIn": {
+ "type": "string"
+ },
+ "amountOut": {
+ "type": "string"
+ },
+ "approval": {
+ "type": "object"
+ },
+ "chainId": {
+ "type": "integer"
+ },
+ "checks": {
+ "type": "object"
+ },
+ "code": {
+ "type": "string"
+ },
+ "deadline": {
+ "type": "string"
+ },
+ "encodedBy": {
+ "type": "string"
+ },
+ "entry": {
+ "type": "string"
+ },
+ "error": {
+ "type": "string"
+ },
+ "exact": {
+ "type": "object"
+ },
+ "executeWith": {
+ "type": "object"
+ },
+ "grossAmountOut": {
+ "type": "string"
+ },
+ "meta": {
+ "type": "object"
+ },
+ "minOut": {
+ "type": "string"
+ },
+ "mode": {
+ "enum": [
+ "preview",
+ "exact"
+ ]
+ },
+ "ok": {
+ "description": "false: see code, error",
+ "type": "boolean"
+ },
+ "protocolVersion": {
+ "type": "string"
+ },
+ "quote": {
+ "type": "object"
+ },
+ "route": {
+ "type": "object"
+ },
+ "tokenIn": {
+ "type": "string"
+ },
+ "tokenOut": {
+ "type": "string"
+ },
+ "tx": {
+ "type": "object"
+ },
+ "txError": {
+ "type": "object"
+ },
+ "unwrapAfter": {
+ "type": "boolean"
+ },
+ "wrapRequired": {
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "ok"
+ ],
+ "type": "object"
+}get_abi1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "abi": {
+ "type": "array"
+ },
+ "code": {
+ "type": "string"
+ },
+ "contract": {
+ "type": "string"
+ },
+ "error": {
+ "type": "string"
+ },
+ "ok": {
+ "description": "false: see code, error",
+ "type": "boolean"
+ },
+ "revision": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "ok"
+ ],
+ "type": "object"
+}get_deployments1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "active": {
+ "type": "object"
+ },
+ "localServer": {
+ "type": "string"
+ },
+ "ok": {
+ "description": "false: see code, error",
+ "type": "boolean"
+ },
+ "schema": {
+ "type": "integer"
+ },
+ "updatedAt": {
+ "type": "string"
+ },
+ "versions": {
+ "type": "array"
+ }
+ },
+ "required": [
+ "ok"
+ ],
+ "type": "object"
+}prepare_quote1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "call": {
+ "type": "object"
+ },
+ "chainId": {
+ "type": "integer"
+ },
+ "code": {
+ "type": "string"
+ },
+ "contracts": {
+ "type": "object"
+ },
+ "curl": {
+ "type": "string"
+ },
+ "decode": {
+ "type": "object"
+ },
+ "error": {
+ "type": "string"
+ },
+ "mode": {
+ "const": "prepare"
+ },
+ "note": {
+ "type": "string"
+ },
+ "ok": {
+ "description": "false: see code, error",
+ "type": "boolean"
+ },
+ "protocolVersion": {
+ "type": "string"
+ },
+ "request": {
+ "type": "object"
+ },
+ "rpcRequest": {
+ "type": "object"
+ }
+ },
+ "required": [
+ "ok"
+ ],
+ "type": "object"
+}prepare_quote1 field changedInput schema / properties / exact / descriptionPrevious value: -"true → previewPlanExact (execution-grade dry-run, no calldata)"New value: +"true → previewPlanExact: every leg dry-run on its pool in this block (no calldata). No tokens move from a holder, so a token that blocks or taxes its own transfer still quotes; simulate the swap from the holder to test that"get_abi1 field changedInput schema / properties / contract / descriptionAdded value: +"quoter (quotes and previews) | router (swap entry point) | solver | hub | core | errors (the protocol custom-error set, for decoding reverts)"decode_quoteget_quoteprepare_quotedecode_quoteget_quoteprepare_quotecheck_solvencydecode_quoteget_abiget_deploymentsget_quoteprepare_quoteget_quote3 fields changedInput schema / properties / deadlineSecAdded value: +{
+ "description": "tx deadline horizon in seconds, 10–3600 (default 120)",
+ "type": "integer"
+}Input schema / properties / exactAdded value: +{
+ "description": "true → execution-grade re-quote (previewPlanExact, slower)",
+ "type": "boolean"
+}Input schema / properties / slippageBpsAdded value: +{
+ "description": "0–5000; minOut = netOut − slippage (default: the protocol floor)",
+ "type": "integer"
+}xray_scanget_quote1 field changedInput schema / properties / rpcAdded value: +{
+ "description": "optional https RPC endpoint of YOUR OWN node — when set, the read is made through it instead of our shared pool. The service stays free either way; this simply keeps your volume off our quota (and off everyone else's).",
+ "type": "string"
+}xray_scan1 field changedInput schema / properties / rpcAdded value: +{
+ "description": "optional https RPC endpoint of YOUR OWN node — when set, the read is made through it instead of our shared pool. The service stays free either way; this simply keeps your volume off our quota (and off everyone else's).",
+ "type": "string"
+}check_solvencyget_quotexray_scan
Add one secure layer between your agents and this server.