
BlazePhoenix MCP server
Which MCP servers are BlazePhoenix's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-15
- Registry namexyz.blazephoenix/mcpverified in the MCP registry
The registry name sits under blazephoenix.xyz. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-15
- Tools4
- Server calls itselfblazephoenix
- Server version2.0.0
- Protocol version2025-06-18
On 2026-10-15 the server answered initialize and tools/list without a sign-in. First answer in 27 ms.
- Whether its tools do the product's job has not been judged yet.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score100 of 100answers 100 · definitions 100 · context 100 · connects 100
- Answered100% of days10 of 10 daily checks
- Median first answer117 ms
- Space in an agent's context≈ 811 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · get a swap quote that can be reproduced at a given block
- cannot · swap tokens without registration or handing over custody
- not sure · verify a quote independently through your own node
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
prepare_quotePrepare 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…
decode_quoteDecode 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)…
get_deploymentsThe 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.
get_abiThe 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…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"blazephoenix": {
"type": "http",
"url": "https://blazephoenix.xyz/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http blazephoenix https://blazephoenix.xyz/mcpclaude.ai, ChatGPT and other clients: add https://blazephoenix.xyz/mcp as a custom connector in the settings.
OpenAPI spec
12 paths, read 2026-10-15. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.