io.github.savhascelik/meta-api-mcp-server
meta-api-mcp-server
You can connect any API to LLMs. This enables AI to interact directly with APIs
alive probed 2026-10-14
70tools
1.7 %of a 200k context window
3.3ktokens, o200k_base estimate
493 msto initialize
9 msto list tools
- Run it
- npx -y meta-api-mcp-server@1.0.4 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- meta-api-mcp-server 1.0.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- The count_tokens endpoint refused the tool schemas: tools.15.custom.input_schema.properties: Property keys should match pattern '^[a-zA-Z0-9_.-]{1,64}$'. The estimate stands in.
- Repository
- https://github.com/savhascelik/meta-api-mcp-server
- Registry
- active, updated 2025-09-09 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| Orders_Retrieveanorder | 138 | 4 % |
| Affiliates_Retrieveanaffiliate | 117 | 4 % |
| OrderItems_Retrieveanorderitem | 99 | 3 % |
| Discounts_Retrieveadiscount | 97 | 3 % |
| Variants_Retrieveavariant | 96 | 3 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.savhascelik/meta-api-mcp-server)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.