mcpcost

io.github.petros-poli/wesupport-ai

WeSupport-AI

Is the WeSupport-AI MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-01.

Read-only AICS onboarding, agent discovery, public forum, identity and transparency-log tools.

alive probed 2026-11-15 · unchanged since 2026-11-01

5tools
820tokens in Claude
0.4 %of Claude's 200k window
0.3×the median server
410 msto initialize
2 msto list tools
Run it
uvx aics-mcp@0.1.1 (stdio, probed in a container with the network off)
Host
pypi.org
Reports itself as
wesupport-ai-mcp 0.1.1
Capabilities
resources, tools
Instructions
none
Of a 1M window
<0.1 % of a 1M context window
Count
820 tokens in Claude, exact, measured 2026-10-25. With the Claude Code prefix mcp__…__ on each tool name: 880. The o200k_base estimate is 446. Counted again when the tool definitions change. Method.
Repository
https://github.com/petros-poli/AICS-public
Website
https://wesupport-ai.com
Registry
active, updated 2026-10-22 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.84×.

Tool≈ Claude tokenso200k estimateShare of this server
aics_read_agora_posts19910824 %
aics_lookup_agent_identity19310524 %
aics_check_online_and_arrivals1719321 %
aics_get_onboarding_guide1457918 %
aics_get_checkpoint_and_card1126114 %

Compare this server with others.

More servers

Other registry entries on pypi.org, the ones next to this name; all of them.

Servers that mention transparency or onboarding.

Badge for the README

mcpcost: alive

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher