Skip to main content
Glama
Sign In

Phase Router

by xyz.phase.ai
OverviewDiscussionsAdmin

Server Details

OpenAI-compatible LLM gateway: pay per request with an API key, signed receipt for each call.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 7 tools

Disambiguation4/5

Most tools target a clearly distinct concern: chat vs embed are different inference modes, quote is explicitly a no-pay price preview, list_models is catalog discovery, receipt is post-payment proof, and key is account/balance state. The only soft overlaps are quote vs chat pricing and session vs receipt (both return shareable/verifiable artifacts), plus `session` bundles four CRUD operations under one name.

Naming Consistency3/5

All names are lowercase snake-ish single tokens, but the conventions are mixed: bare verbs (chat, embed, quote) sit alongside bare nouns (key, receipt, session) and one verb_noun (list_models). Readable, but there is no predictable pattern an agent can rely on to infer new tool names.

Tool Count5/5

Seven tools is well-scoped for a paid LLM gateway: inference, embeddings, pricing, catalog, account state, receipts, and sessions each cover a real need. No obvious filler or redundant tools.

Completeness4/5

The surface covers the full pay-per-call lifecycle: discover models, quote, execute (chat/embed), inspect spend, and verify receipts with Merkle proofs, plus multi-turn sessions. Minor gaps exist — wallet-mode balance/spend is only partly addressed via `key` (key mode) and `session` listing, and there is no explicit history/transaction listing tool.

Available Tools

7 tools
chatB
Destructive
Inspect

Run a chat completion on Phase Router, paid from the Phase API key or the wallet this server uses (free models cost nothing). Returns the answer, actual price, task id for the receipt and usage.

Inputs: model (required), prompt, system, session, +3 more. Returns: text, batch, level, model, +12 more

embedC
Destructive
Inspect

Compute embeddings on Phase Router (paid from the Phase API key or the wallet).

Inputs: input (required), model (required). Returns: payment, vectors, price_usd

keyA
Read-only
Inspect

Balance, daily cap and spend of the Phase API key this server pays with (key mode).

Returns: key

list_modelsA
Read-only
Inspect

List models of Phase Router with prices (USD per 1M tokens, fee per call) and layer (flagship | open | class | free).

Inputs: layer. Returns: models, wallet, gateway

quoteB
Read-only
Inspect

Get the price ceiling for a chat request without paying (the gateway's 402 quote).

Inputs: model (required), prompt, system, session, +3 more. Returns: free, model, network, ceiling_usd, +8 more

receiptA
Read-only
Inspect

Fetch the public receipt of a paid request by task id (model, provider, tokens, price, settlement tx, request/response hashes, signatures) and its Merkle proof once the weekly epoch is closed.

Inputs: task_id (required). Returns: url, proof, receipt, epoch_state

sessionA
Destructive
Inspect

Saved chat sessions on Phase Router: create one (returns an id and a shareable /s/ link), read its thread, list the wallet's sessions (wallet mode only: signed with the wallet key, no transaction), or delete one. Pass the id as session to chat and the gateway carries the context between turns and visits.

Inputs: action (required), id, model, title, +1 more. Returns: id, url, model, title, +7 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • farebox-mcp

      fareboxfun
      A
      license
      Not graded
      quality
      C
      maintenance
      Crypto-native LLM gateway with OpenAI-compatible API and per-token USDC payments on Solana via the x402 protocol.
      9,226 npm
      MIT

    • omnicall-mcp

      ColinHughes2121
      F
      license
      Not graded
      quality
      C
      maintenance
      Keyless, pay-per-call AI gateway: 248 LLMs plus image/video/voice/music generation and live crypto, DeFi, markets, web-search and research tools through one MCP server. Pay per call in USDC via x402 on Base/Solana — no API key, no signup, free tier.
      -

    • proxyllm-mcp

      proxyllm-ai
      A
      license
      A
      quality
      D
      maintenance
      MCP server for ProxyLLM, the OpenAI-compatible LLM gateway, enabling live model catalogs, plan-savings calculations, routing key management, and autonomous account signup.
      9
      135 npm
      MIT

    • @bsvkey/inference-mcp

      BSVKey
      A
      license
      A
      quality
      B
      maintenance
      Enables any agent to purchase Claude and Grok inference metered per token, settled in BSV, via the hosted gateway without holding keys or running models locally.
      4
      207 npm
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources