Agents Index

Cap Shield

Online

Context selection and compression for AI agents - recall measured, not claimed.

Visit publisherConnectJSON

What it can do: 9 tools

  • measure_traffic read-onlyMeasure how much of your own agent traffic could be saved. NO ACCOUNT OR KEY NEEDED — use this first. Returns byte savings over the wire and, if a query is given, token savings from selective context retrieval. Nothing i
  • list_packages read-onlyList the available dictionaries with their MEASURED compression, including the ones that perform badly. Each entry says whether it works one message at a time or only batched, and how many messages came out LARGER. No ke
  • rememberStore a memory entry for later retrieval. REQUIRES A KEY. This does not call any language model — it stores text in an isolated per-tenant archive. Use assemble_context to get relevant entries back.
  • assemble_context read-onlyRetrieve the memory entries that answer a question, within a token budget. REQUIRES A KEY. Send the returned 'context' to your language model INSTEAD of the whole history. This does not call a model itself — it selects w
  • assemble_escalation_context read-onlyRetrieve a WIDE context for a question your model could not answer from assemble_context. REQUIRES A KEY. Use it when assemble_context returned escalate_recommended=true, or when the answer depends on dates, counts or se
  • get_accountGet an account and an API key. Requires an email address. The key is returned ONCE and cannot be shown again — store it immediately. Beta quotas are low by design; they are hard stops, never overage billing.
  • issue_passIssue a short-lived (15 minute) signed credential (a JWT) stating who the caller acts for. REQUIRES A KEY. Anyone can verify it independently against /.well-known/jwks.json — without calling CAP-Shield again. 'acts_for'
  • pack_batch read-onlyPack several messages into ONE compressed packet instead of packing them one at a time. REQUIRES A KEY. Worth it for many small/medium messages (the per-message header cost is paid once per batch, and zstd shares context
  • unpack_batch read-onlyUnpack a batch packet made by pack_batch (or by the /api/v1/pack-batch endpoint) back into the exact original list of messages, in order. REQUIRES A KEY. Not for a packet made by the single-message pack endpoint — that i

Connect it

Claude Code
claude mcp add --transport http cap-shield https://cap-shield-robin.fly.dev/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://cap-shield-robin.fly.dev/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "cap-shield": {
      "url": "https://cap-shield-robin.fly.dev/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "cap-shield": {
      "type": "http",
      "url": "https://cap-shield-robin.fly.dev/mcp"
    }
  }
}

Questions

What does Cap Shield do?

Context selection and compression for AI agents - recall measured, not claimed. It exposes 9 tools to AI assistants.

What tools does Cap Shield provide?

9 tools, including measure_traffic, list_packages, remember, assemble_context, assemble_escalation_context, get_account, issue_pass, pack_batch, unpack_batch.

How do I connect Cap Shield to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://cap-shield-robin.fly.dev/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Cap Shield require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Cap Shield online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Cap Shield?

@robinlidberg-dot on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Agents & Orchestration