loading…
Search for a command to run...
loading…
An MCP server that helps AI agents reduce token usage by compressing, summarizing, and managing conversation/context data more efficiently.
An MCP server that helps AI agents reduce token usage by compressing, summarizing, and managing conversation/context data more efficiently.
A token-saving MCP proxy for OpenClaw users. Cuts tool call payloads by 90%+ via lazy expansion.
MCP tool calls often return thousands of tokens of HTML or JSON in a single response — but the model typically uses only 5% of it. The remaining 95% silently burns context window and increases cost. claw-tsaver sits between OpenClaw and your downstream MCP servers, intercepts oversized responses, and hands the model a compact preview + an on-demand handle instead.
sequenceDiagram
participant U as OpenClaw (Claude)
participant C as claw-tsaver proxy
participant F as fetch / puppeteer / etc.
U->>C: call_tool("fetch", url)
C->>F: forward call
F-->>C: 11,507 tokens of HTML
Note over C: tiktoken count > threshold
C->>C: store full content in SQLite
C-->>U: {preview_head, preview_tail, expand_handle}<br/>(only 104 tokens)
Note over U: model decides if it needs full text
U->>C: expand_content(handle)
C-->>U: full 11,507 tokens
| Test | Original tokens | Returned tokens | Saved |
|---|---|---|---|
| fetch Wikipedia "Tokenization (data security)" | 11,507 | 104 | 99.1% |
Tested on OpenClaw + Claude Sonnet 4.6 + mcp-server-fetch, 2026-04-25.
Raw data: benchmarks/mvp-day1-fetch.jsonl.
Install uv (one-time setup):
curl -LsSf https://astral.sh/uv/install.sh | sh
No claw-tsaver install needed — uvx will fetch and run it on demand.
Edit ~/.claw-tsaver/config.json (first run of claw-tsaver-mcp will auto-create a template):
{
"downstream_servers": [
{"name": "fetch", "command": "uvx", "args": ["mcp-server-fetch"]}
],
"compression_threshold_tokens": 500
}
Add this block at the top level of ~/.openclaw/openclaw.json:
"mcp": {
"servers": {
"claw-tsaver": {
"command": "uvx",
"args": ["--from", "git+https://github.com/Yang1Bai/claw-tsaver",
"claw-tsaver-mcp"]
}
}
}
Then restart OpenClaw gateway: openclaw gateway restart
Optional: a local web UI for real-time token savings stats.
uvx --from git+https://github.com/Yang1Bai/claw-tsaver claw-tsaver-dashboard
Open http://localhost:7878 in your browser.
MIT — see LICENSE file.
Issues and PRs welcome.
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"claw-tsaver": {
"command": "npx",
"args": []
}
}
}Web content fetching and conversion for efficient LLM usage.
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolProvides auto-configuration for setting up an MCP server in Spring Boot applications.
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hz