Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

fix(mcp): pin mcp dependency to <2.0.0 to prevent server startup crash (#2642)

Robert Schorrb3f016b86637
diff --git a/pyproject.toml b/pyproject.toml
index 1a43c32c5..6e1b1ba48 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -78,7 +78,7 @@ proxy = [
"orjson>=3.9.14; platform_python_implementation != 'PyPy'",
"httpx[http2]>=0.24.0",
"openai>=2.14.0", # OpenAI API format support
- "mcp>=1.28.1", # MCP server (headroom_compress, retrieve, stats)
+ "mcp>=1.28.1,<2.0.0", # MCP server (headroom_compress, retrieve, stats)
"magika>=0.6.0", # ML content detection for ContentRouter
"zstandard>=0.20.0", # Decompress zstd request bodies (Codex, etc.)
"websockets>=13.0", # WebSocket proxy for /v1/responses (Codex gpt-5.4+)
@@ -225,7 +225,7 @@ autogen = [
]
# MCP server for Claude Code integration
mcp = [
- "mcp>=1.28.1",
+ "mcp>=1.28.1,<2.0.0",
"httpx>=0.24.0",
"starlette>=0.27.0",
"uvicorn>=0.23.0,<1.0",