Skip to content
Open App

MCP Server — Limits, Timeouts, and Performance Notes

The Picasi MCP server is designed for fast data access (< 5 seconds). This page lists the current technical limits and timeout rules so that AI assistants can properly scale their requests.

Tool Limits

Limits per tool call, as currently accepted by the server.

search_updates

ParameterLimit
limit1 – 100 (default: 20)
days1 – 365 (default: 7)
date_from / date_toAny time period; overrides days

If limit is set to more than 100, the server truncates the value to 100 and indicates this in the meta block (total_available shows the actual available count).

list_sources

No hard upper limits. The response contains all sources in the workspace. For very large workspaces, include_channels: false (default) is recommended to keep the payload small.

list_reports

ParameterLimit
limitDefault 10, no known hard upper limit

All Other Tools

There are no hard response limits for get_update_details, get_report, get_team_context, list_tags, or the write tools. Payloads are tied to the resource (a report, an update, a team).

Response Times

Data queries are optimized for sub-second response times.

ToolExpected Response Time
search_updatestypically < 1 s
list_sourcestypically < 1 s (without channels)
list_sources with include_channels: true1–3 s (workspace-dependent)
get_update_detailstypically < 1 s
get_report1–3 s (report-dependent)
get_team_contexttypically < 1 s
Write tools (create_*, update_*, delete_*, toggle_*)typically < 2 s

MCP Timeouts

The Picasi server does not enforce its own server timeout. The timeouts of the respective AI clients apply.

ClientEffective Client Timeout
Claude Code (CLI)Default 30 s per tool call
Claude.aiDefault 30 s per tool call
ChatGPT (Custom Connector)Default 30 s per tool call

Therefore, analysis tools with long runtimes (generate_feedback, summarize_updates — 15 to 45 seconds) are currently disabled. For longer analyses, use the Picasi app or retrieve the results of a previously generated report via get_report.

Rate Limiting

The MCP server currently uses no dedicated rate-limiting middleware. The general protection mechanisms of the Picasi platform (auth rate limits, WAF) apply.

Recommendations for client implementations:

  • Cache results when identical queries are made repeatedly.
  • For bulk evaluations, set limit explicitly instead of paginating through small pages in a loop.
  • For multiple parallel requests, prefer a single tool call per logical query.

As soon as the MCP server enforces rate limiting, this page will be updated with figures and HTTP header behavior (Retry-After, X-RateLimit-*).

Payload Structure

All tool responses provide three blocks:

  • result – Payload (updates, sources, reports, …)
  • meta – Execution time, applied filters, total_available for searches
  • hints – Suggestions for useful follow-up calls

total_available in meta shows how many results would be available in total, even if they were not returned. This allows the client to decide whether a targeted query is worthwhile.