{"domain":"tokenzero.sh","name":"TokenZero","url":"https://inite.ai/en/atlas/tokenzero.sh","site":"https://tokenzero.sh","summary":"Routes LLM API calls through a proxy that adds prompt caching, exact-response caching and a signed savings ledger.","forWhom":"Developers and teams paying OpenAI, Anthropic or Gemini API bills who want to cut token spend.","useCases":["route LLM API calls through a gateway to reduce spend","make prompts cache-friendly without changing their content","scan a codebase for uncached prompts and costly model choices"],"categories":["llmops"],"pricing":{"model":"freemium","freeTier":true,"startsAt":{"amount":1790,"currency":"USD","per":"year","billed":"yearly"},"page":"https://tokenzero.sh/#pricing","readOn":"2026-10-29"},"priceMoves":[],"interfaces":{"readOn":"2026-10-29","apiDocs":"https://tokenzero.sh/openapi.json","openapi":{"url":"https://tokenzero.sh/openapi.json","paths":30,"title":"TokenZero Gateway"},"mcp":[{"name":"io.github.tokenzero-ai/tokenzero","tie":"github","registered":true,"remotes":["https://tokenzero.sh/mcp"],"packages":[],"probe":{"state":"open","checkedOn":"2026-10-29","toolCount":5,"tools":["audit_repo_token_waste","optimize_prompt_payload","calculate_model_arbitrage","provision_workspace","workspace_metrics"],"serverName":"tokenzero"}},{"name":"sh.tokenzero/mcp","tie":"namespace","registered":true,"remotes":["https://api.tokenzero.sh/mcp"],"packages":["npm"],"probe":{"state":"open","checkedOn":"2026-10-29","toolCount":5,"tools":["audit_repo_token_waste","optimize_prompt_payload","calculate_model_arbitrage","provision_workspace","workspace_metrics"],"serverName":"tokenzero"}}],"mcpServerCard":null,"status":null},"mcpMeasured":{"server":"https://api.tokenzero.sh/mcp","checkedSince":"2026-10-29","dailyChecks":4,"uptimePercent":null,"medianMs":224,"signIn":"none","clientRegistration":null,"tools":6,"contextTokens":1066,"definitionsGrade":"A","definitionsScore":92,"typedResults":0,"failingChecks":{"params_described":3},"warnings":{},"coverage":{"share":1,"cases":[{"useCase":"route LLM API calls through a gateway to reduce spend","verdict":"covered","firstTool":null,"checks":null},{"useCase":"make prompts cache-friendly without changing their content","verdict":"unsure","firstTool":null,"checks":null},{"useCase":"scan a codebase for uncached prompts and costly model choices","verdict":"covered","firstTool":"audit_repo_token_waste","checks":null}]},"adoption":{"npmWeekly":2991,"pypiWeekly":null,"githubStars":0},"score":null,"advice":{"verdict":"unproven","why":["its tools do every use case checked: \"route LLM API calls through a gateway to reduce spend\", \"scan a codebase for uncached prompts and costly model choices\"","checked on 4 of the 7 days it takes to judge reliability"],"how":["for \"scan a codebase for uncached prompts and costly model choices\", the likely first call is audit_repo_token_waste","parameters are untyped or undescribed in 3 of 6 tools: check arguments before calling"]},"method":"https://inite.ai/en/atlas/mcp/report"},"connect":{"order":["mcp","openapi","apiDocs","llmsTxt"],"mcp":[{"name":"io.github.tokenzero-ai/tokenzero","url":"https://tokenzero.sh/mcp","answers":"open","checkedOn":"2026-10-29","weakTie":false,"registry":"https://registry.modelcontextprotocol.io/v0/servers?search=io.github.tokenzero-ai%2Ftokenzero","config":{"mcpServers":{"tokenzero":{"url":"https://tokenzero.sh/mcp"}}},"install":{"transport":"http","claudeCode":"claude mcp add --transport http tokenzero https://tokenzero.sh/mcp","cursor":"cursor://anysphere.cursor-deeplink/mcp/install?name=tokenzero&config=eyJ1cmwiOiJodHRwczovL3Rva2VuemVyby5zaC9tY3AifQ%3D%3D","vscode":"vscode:mcp/install?%7B%22name%22%3A%22tokenzero%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Ftokenzero.sh%2Fmcp%22%7D","connector":{"url":"https://tokenzero.sh/mcp","note":"Add it as a custom connector in the client’s settings; the client opens the sign-in itself when the server asks for one."}}},{"name":"sh.tokenzero/mcp","url":"https://api.tokenzero.sh/mcp","answers":"open","checkedOn":"2026-10-29","weakTie":false,"registry":"https://registry.modelcontextprotocol.io/v0/servers?search=sh.tokenzero%2Fmcp","config":{"mcpServers":{"tokenzero":{"url":"https://api.tokenzero.sh/mcp"}}},"install":{"transport":"http","claudeCode":"claude mcp add --transport http tokenzero https://api.tokenzero.sh/mcp","cursor":"cursor://anysphere.cursor-deeplink/mcp/install?name=tokenzero&config=eyJ1cmwiOiJodHRwczovL2FwaS50b2tlbnplcm8uc2gvbWNwIn0%3D","vscode":"vscode:mcp/install?%7B%22name%22%3A%22tokenzero%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.tokenzero.sh%2Fmcp%22%7D","connector":{"url":"https://api.tokenzero.sh/mcp","note":"Add it as a custom connector in the client’s settings; the client opens the sign-in itself when the server asks for one."}}}],"openapi":{"url":"https://tokenzero.sh/openapi.json","paths":30},"apiDocs":"https://tokenzero.sh/openapi.json","llmsTxt":"https://tokenzero.sh/llms.txt","status":null,"readOn":"2026-10-29"},"trust":{"readOn":"2026-10-29","certifications":[],"training":null},"used":null,"alive":100,"traits":{"buyer":null,"deployment":"saas-only","developerFocus":true,"readAt":"2026-10-29"},"verifiedPlans":null,"fromVendor":null}