mcp-context-budget
Related Servers
Alternatives to mcp-context-budget
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables auditing MCP servers' tools by their estimated context token cost, ranking verbose names, descriptions, and schemas before they consume the agent window. Can run as an MCP tool so agents can budget their own context.1MIT
- AlicenseNot gradedqualityDmaintenanceDiagnoses MCP server token costs, finds duplicates, grades efficiency, and generates optimization reports.65 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables analyzing and optimizing context window token usage by measuring, compressing, and eliminating waste from MCP tool definitions.63 npmMIT
- AlicenseNot gradedqualityAmaintenanceProvides tool to count token cost of any MCP server's tool definitions, enabling agents to assess cost before enabling.41 PyPIMIT
- AlicenseAqualityAmaintenanceMeasures what MCP servers cost in context tokens: probes a URL or a local command now, measures a whole config file, and looks up the daily results for every server in the official MCP registry on mcpcost.ulehla.dev.62MIT
- AlicenseAqualityCmaintenanceMCP server that scores tool descriptions, estimates token costs, simulates agent tool selection, and generates reliability reports to help AI agents choose the right tools and reduce wasted tokens.59 npmMIT
TDQS
Scored across 3 tools
explain_token_cost is clearly separate (arbitrary schema/text estimation) from the two server-inventory tools. audit_context_budget and rank_servers_by_cost target the same data with different depth, but the descriptions explicitly frame them as full report vs. cheap ranking, so confusion is limited though real.
All three follow a clean verb_noun snake_case pattern (audit_*, rank_*, explain_*). The noun components vary sensibly with what each acts on.
Three tools is on the thin side, but the domain (context-cost measurement) is narrow and each tool covers a distinct query pattern. No filler tools are present.
Covers the core lifecycle: full audit, quick ranking, and ad-hoc schema/text estimation. Minor gaps exist — no single-server targeted query or budget-threshold/warning configuration — but agents can reach the same answers through the provided tools.