A paid remote MCP that wraps OpenAI Codex's context compression features for token reduction workflows. Exposes four tools: compress_context_for_task, estimate_context_savings, issue_context_receipt, and read_compression_history. Requires a bearer token from the product website and runs over streamable HTTP, so you don't host anything. The receipt and history tools suggest this is built for teams that need audit trails on what context was compressed and how much was saved. Reach for it when you're burning through prompt tokens on large codebases and want verifiable compression logs rather than ad hoc chunking.
Hosted MCP for OpenAI Codex context compressor.
RTK Context Compressor is a paid remote MCP endpoint for OpenAI Codex context compressor. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-ready workflow evidence for AI agents and coding teams.
com.clauxel.rtkcontext/rtkcontext-mcpThis is a paid hosted remote MCP. Production calls require a bearer token issued from the product website.
Authorization: Bearer <token>
Unauthenticated browser visits to /mcp return a clear JSON error instead of internal details.
compress_context_for_taskestimate_context_savingsissue_context_receiptread_compression_historyThis repository is a public documentation and directory-submission reference for the hosted service. It does not contain the private production source code.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent