io.github.tathagat22/slipstream
mcp-typescript server on vercel
io.github.tathagat22/slipstream costs 1 182 tokens of context per session. It has 8 tool definitions. That is 0.6 % of a 200k window. Measured 2026-10-03.
Shared distillation cache for AI agents — every fetch ~73-89% fewer tokens via a shared cache.
alive probed 2026-10-03 · HTTP 200
8tools
1.2ktokens for the tool definitions
0.6 %of a 200k context window
2.6 sto initialize
123 msto list tools
- Endpoint
- https://slipstream-pi.vercel.app/api/mcp (streamable-http)
- Host
- slipstream-pi.vercel.app
- Protocol
- 2025-11-25
- Reports itself as
- mcp-typescript server on vercel 0.1.0
- Capabilities
- tools
- Instructions
- none
- Repository
- https://github.com/tathagat22/slipstream
- Website
- https://slipstream-pi.vercel.app
- Registry
- active, updated 2026-06-01 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| cached_fetch | 312 | 26 % |
| slipstream_note | 239 | 20 % |
| whats_new | 189 | 16 % |
| slipstream_recall | 103 | 9 % |
| slipstream_flag | 102 | 9 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:40 | alive | 2.6 s | 8 | 1.2k |
| 2026-10-03 17:55 | alive | 579 ms | 8 | 1.2k |
Badge
[](https://mcp-pulse.ulehla.dev/s/io.github.tathagat22/slipstream)