# Reported issues for PraisonAI

Pod holds 24 of 72 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to [PraisonAI](/mcp/praisonai).

## Most discussed

### praisonai test collection requires optional modules in default setup

# `praisonai` test collection requires optional modules in default setup

## Problem Statement
`praisonai` tests fail during collection in a base editable install because test/import paths assume optional integrations are installed (`praisonaiui`, `google.generativeai`).

## Why This Matters
A default dev install should run baseline tests. Optional integrations should not break core test collection.

## Environment
- OS: Windows 10 (build 19045)
- Python: 3.13.2
- Repo: `MervinPraison

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/1541) · 2026-04-24 · closed · outside contributor · 5 comments

### GNAP: git-native task persistence for PraisonAI multi-agent workflows

Hi PraisonAI team 👋

PraisonAI's focus on low-code multi-agent systems that deliver to Telegram, Discord, and WhatsApp resonates with real-world deployment patterns. I wanted to share a coordination protocol that could add durability to PraisonAI's multi-agent pipelines.

**[GNAP](https://github.com/farol-team/gnap)** (Git-Native Agent Protocol) turns any git repo into a zero-server coordination layer for AI agents. No Redis, no Celery, no extra services — just 4 JSON files and git push/pull.

*

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/1117) · 2026-03-15 · open · external user · 7 comments

### AI Agent don't use tool || issue

i wrote a simple code like this:

"""""""""
import logging
logging.basicConfig(level=logging.DEBUG)
import posthog
posthog.disabled = True
import os
import sys
import litellm
litellm.extra_body = {
"chat_template_kwargs": {"enable_thinking": False},
"tool_choice": "auto",
"tool_call_parser": "hermes",
}
import gradio as gr
from praisonaiagents import Agent, MCP
import httpx
os.environ["GRADIO_ANALYTICS_ENABLED"] = "False"
import requests
requests.packages.urllib3.disable_warnings()
litellm.clien

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/1077) · 2025-08-01 · closed · external user · 8 comments

### Support MCP with HTTP-Streaming

Updated standard for MCP is now HTTP-Streaming instead of SSE. Would be great, if you cloud update, so that MCP-Server with HTTP-Streaming cloud be integrated as well.

Best
Grabow

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/722) · 2025-07-01 · closed · external user · 29 comments

### Timeout with MCP inisitailization

First off thanks for the framwork a great time saver

I am getting a timeout

![Image](https://github.com/user-attachments/assets/ab0aa38e-8edb-4f0c-835d-6df80efe4d0d)

Itried increasing timeout it did not work
    agent = Agent(
        instructions="You help do operation on Kites.",
        llm="gpt-4o-mini",
        tools=MCP("npx @mcp-remote https://mcp.kite.trade/sse",timeout=60000),
        )
    result = agent.start(query)

But I could use this MCP with MCP Inspector.

![Image](https://g

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/483) · 2025-05-21 · closed · external user · 14 comments

### MCP doesn't work in Streamlit

Hi, I am have a MCP server running with Python. It works normally when I write a Python client script. But it doesn't work when I publish it to the Streamit app. It seems that the MCP can be initialized in Streamlit but when I make a query, it just could not fetch the MCP tool. I have tried running these piece of code, but the MCP tool cannot be found neither. Mind help look into this or maybe provide a working example of integrating MCP to Streamlit?

import streamlit as st
from praisonaiagents

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/459) · 2025-04-10 · closed · external user · 7 comments

### ModuleNotFoundError: No module named 'mcp'

@MervinPraison  I referred to the closed issue #439. But that did not solve the problem.
`pip install -U "praisonaiagents[mcp]"`

M1 Mac.

Using the sample script 

`from praisonaiagents import Agent, MCP

search_agent = Agent(
    instructions="""You help book apartments on Airbnb.""",
    llm="gpt-4o-mini",
    tools=MCP("npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt")
)

search_agent.start("I want to book an apartment in Paris for 2 nights. 03/28 - 03/30 for 2 adults")
`
from https:

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/445) · 2025-04-02 · closed · external user · 14 comments

### MCP Tools SSE Support

@MervinPraison Is there any existing support for MCP tools in the Praison AI ?

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/426) · 2025-03-18 · closed · external user · 6 comments

## Most recent

### MCP npx server-time yields zero tools on Windows and can ACCESS_VIOLATION the interpreter

# [BUG] `tools=MCP("npx -y @modelcontextprotocol/server-time")` yields zero tools on Windows and can ACCESS_VIOLATION the interpreter

## Metadata

| Field | Value |
|-------|-------|
| **Repository** | https://github.com/MervinPraison/PraisonAI |
| **Package** | `praisonaiagents` (`praisonaiagents.mcp.MCP`) |
| **Version tested** | **1.7.1** worktree, `origin/main` `@ 689978100` |
| **Labels** | `bug`, `mcp`, `npx`, `windows`, `silent-failure`, `process-crash` |
| **Severity** | **Hig

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/4375) · 2026-08-26 · closed · outside contributor · 3 comments

### [Feature] Add an official HOL Guard wrap_tool_call security example

### Summary

Add a small official PraisonAI example/recipe showing how to use HOL Guard at the existing `wrap_tool_call` middleware boundary before a command-bearing tool executes.

### Why this fits PraisonAI

PraisonAI already exposes `@wrap_tool_call` specifically so middleware can either call `call_next(request)` or short-circuit before the underlying tool runs. That makes it a clean integration point for an external runtime security engine without adding a new PraisonAI core API or dependen

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/4278) · 2026-08-24 · closed · outside contributor · 3 comments

### EvalPort adapter for praisonaiagents.eval (EvalCase/EvalResult/EvalPackage)

I've been looking at `praisonaiagents.eval` (`src/praisonai-agents/praisonaiagents/eval/`) and it's one of the more portable-looking eval data models I've seen in an agent framework — worth pointing out for interop.

**What EvalPort is:** an open spec + SDK (`evalport-sdk` on PyPI, `openeval.validate.validate_suite()` / `validate_result_set()`) for representing LLM eval suites and results in a framework-neutral JSON format, so a suite built in one tool can run against another's harness and resul

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/4275) · 2026-08-23 · open · external user · 1 comment

### [Feature] TealTiger as a guardrails provider — deterministic PII/secret detection, prompt injection defense, and regulatory policy templates

### Problem

PraisonAI's `guardrails=` parameter and built-in `approval=True` cover basic governance, but regulated industries need more depth:

1. **PII detection with regulatory coverage** — Healthcare agents need all 18 HIPAA PHI identifiers detected. Financial agents need credit card, account number, SSN detection. Current guardrails don't cover these.

2. **Prompt injection defense** — Agents consuming external data (MCP servers, web fetch, RAG) are vulnerable to adversarial inputs in tool 

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/4262) · 2026-08-23 · open · external user · 2 comments

### ACP IDE server constructs a tool-less chat `Agent`: MCP configs, write/shell flags, and session capabilities never reach the model loop

# Executive Summary

`praisonai acp` / `praisonai serve acp` is documented as an **Agent Client Protocol** server for Zed, JetBrains, VS Code, and Toad. Editors speak JSON-RPC over stdio and expect a coding agent that can read/write files, run commands, honor permissions, and optionally attach MCP servers supplied by the client.

A live in-process handshake on `main` @ `43bea02` shows the opposite:

- `initialize` advertises `promptCapabilities.image: false`, `mcpCapabilities.http/sse: false`, a

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3931) · 2026-08-14 · closed · outside contributor · 3 comments

### Pre-compaction memory flush before ContextCompactor summarises or discards turns

# Title

Pre-compaction memory flush — extract durable user facts into memory **before** `ContextCompactor` summarises or discards turns

# Executive Summary

PraisonAI ships a mature context-budget stack: `ExecutionConfig.context_compaction`, `ContextCompactor` in `compaction/compactor.py`, `BEFORE_COMPACTION` / `AFTER_COMPACTION` hooks, session `append_compaction_checkpoint`, `LearnManager`, memory adapters, and opt-in `self_improve` skill capture. Together these protect token budgets an

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3760) · 2026-08-06 · closed · outside contributor · 2 comments

### `ExecutionConfig.max_rpm` is a dead field — docs and examples claim RPM limiting works, but Agent never builds a `RateLimiter`

# Executive Summary

`ExecutionConfig.max_rpm` is accepted, stored on the agent as `self.max_rpm`, printed by examples, and documented as “Only N requests per minute” — yet **no `RateLimiter` is ever created from it**. Runtime rate limiting only activates when an explicit `rate_limiter=` object is passed. Setting `max_rpm` alone leaves `agent._rate_limiter is None`, so chat/execution mixins never call `acquire()` and the agent fires LLM requests unbounded.

Validated on **praisonaiagents 1.6.164

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3701) · 2026-08-06 · open · outside contributor · 3 comments

### [BUG] `delegate_task` tool always fails — sub-agent runtime not wired

# [BUG] `delegate_task` tool always fails — sub-agent runtime not wired

## Metadata

| Field | Value |
|-------|-------|
| **Repository** | https://github.com/MervinPraison/PraisonAI |
| **Package** | `praisonaiagents` |
| **Version tested** | 1.6.163 on `main` (`PraisonAI-main-e2e`) |
| **Labels** | `bug`, `praisonaiagents`, `tools`, `multi-agent`, `delegation` |
| **Severity** | **High** — public tool API is non-functional; misleads developers |
| **Component** | `src/praisonai-age

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3649) · 2026-08-04 · closed · outside contributor · 2 comments

### [Enhancement] Add Runtime Context Providers for live external data (Slack, GDrive, Gmail, Wiki, MCP) — Agno parity gap

# Runtime Context Providers — Live Slack, Google Workspace, Wiki, and MCP Data Injection

## Title

**[Enhancement] Add Runtime Context Providers for live external data (Slack, GDrive, Gmail, Wiki, MCP) — Agno parity gap**

---

## Executive Summary

Agno ships a first-class **`context/` module** with built-in providers for Slack, Google Drive, Gmail, wikis, web search, MCP servers, calendars, and filesystem workspaces. These inject **live external data as natural-language tools** at a

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3523) · 2026-07-30 · closed · outside contributor · 2 comments

### [BUG][Flaky] Bot gateway E2E sandbox message check fails — agent omits E2E_SANDBOX_OK marker

# [BUG][Flaky] Bot gateway E2E sandbox message check fails — agent omits `E2E_SANDBOX_OK` marker

## Metadata

| Field | Value |
|-------|-------|
| **Repository** | https://github.com/MervinPraison/PraisonAI |
| **Labels** | `bug`, `praisonai-bot`, `sandbox`, `e2e`, `flaky-test` |
| **Severity** | **Medium** — intermittent live E2E failure; sandbox path may work but validation is unreliable |
| **Component** | `e2e-platform-audit/bot_gateway_e2e.py`, `BotHandler._build_tools`, agent to

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3501) · 2026-07-29 · closed · outside contributor · 2 comments

### [BUG][Windows] MCP praisonai.rules.create unit test fails — fixture sets HOME but not USERPROFILE

# [BUG][Windows] MCP `praisonai.rules.create` unit test fails — fixture sets `HOME` but not `USERPROFILE`

## Metadata

| Field | Value |
|-------|-------|
| **Repository** | https://github.com/MervinPraison/PraisonAI |
| **Labels** | `bug`, `windows`, `testing`, `mcp`, `security` |
| **Severity** | **Medium** — Windows CI/dev test suite fails; path-safety regression tests incomplete on Windows |
| **Component** | `src/praisonai/tests/unit/mcp/test_rules_path_safety.py` |
| **Related**

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3500) · 2026-07-29 · closed · outside contributor · 2 comments

### [BUG][Windows][Regression] bot_gateway_e2e.py still crashes cp1252 stdout after gateway #3475 fix

# [BUG][Windows][Regression] `bot_gateway_e2e.py` still crashes cp1252 stdout after gateway `#3475` fix

## Metadata

| Field | Value |
|-------|-------|
| **Repository** | https://github.com/MervinPraison/PraisonAI |
| **Labels** | `bug`, `windows`, `praisonai-bot`, `e2e`, `developer-experience`, `regression` |
| **Severity** | **Medium** — live browser E2E still unusable on default Windows console; masks Playwright install hint |
| **Component** | `e2e-platform-audit/bot_gateway_e2e.p

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3499) · 2026-07-29 · open · outside contributor · 4 comments

### [BUG][Windows] Bot gateway E2E browser check crashes on cp1252 when Playwright stderr contains box-drawing characters

# [BUG][Windows] Bot gateway E2E browser check crashes on cp1252 when Playwright stderr contains box-drawing characters

## Metadata

| Field | Value |
|-------|-------|
| **Repository** | https://github.com/MervinPraison/PraisonAI |
| **Labels** | `bug`, `windows`, `praisonai-bot`, `browser`, `developer-experience`, `e2e` |
| **Severity** | **Medium** — browser validation path broken on default Windows terminals; masks real Playwright install error |
| **Component** | `e2e-platform-aud

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3430) · 2026-07-27 · closed · outside contributor · 3 comments

### [BUG] MCP wrapper unit tests fail collection without `praisonai-mcp` on PYTHONPATH / dev extra

# [BUG] MCP wrapper unit tests fail collection without `praisonai-mcp` on PYTHONPATH / dev extra

## Metadata

| Field | Value |
|-------|-------|
| **Repository** | https://github.com/MervinPraison/PraisonAI |
| **Labels** | `bug`, `testing`, `mcp`, `developer-experience`, `monorepo` |
| **Severity** | **Medium** — default contributor test workflow breaks on MCP unit tests |
| **Component** | `src/praisonai/tests/unit/mcp/`, `pyproject.toml` `[dev]` extra, C12 shim bootstrap |
| **Aff

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3425) · 2026-07-27 · closed · outside contributor · 2 comments

### Replace shared API keys on praisonai serve with JWT scope RBAC and service account PATs

# Production Runtime Auth — JWT Scope RBAC and Service Accounts for `praisonai serve`

## Title

Replace single shared API keys on `praisonai serve` with JWT scope RBAC, service account PATs, and route-level authorization matching enterprise agent platform expectations

---

## Executive Summary

Agno AgentOS v2.8.0 implements production-grade API authentication via `JWTMiddleware` (`libs/agno/agno/os/middleware/jwt.py`) with:
- Granular **`AgentOSScope`** enum (`resource:action`, wil

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3329) · 2026-07-23 · closed · outside contributor · 2 comments

### Add ContextProvider protocol and built-in providers for live organizational context (Slack, Drive, Wiki, MCP, Web)

# First-Class Context Providers for Live External Data (Slack, Drive, Wiki, MCP, Web)

## Title

Add `ContextProvider` protocol and built-in providers so agents query live organizational context without bespoke tool wiring

---

## Executive Summary

PraisonAI agents today receive context through RAG/knowledge bases, memory, and ad-hoc tools. Agno v2.8.0 ships a unified **`ContextProvider`** abstraction (`libs/agno/agno/context/provider.py`) with implementations for filesystem, web sea

[Read the thread](https://github.com/MervinPraison/PraisonAI/issues/3328) · 2026-07-23 · closed · outside contributor · 2 comments

The remaining reports are on [the project's issue tracker](https://github.com/MervinPraison/PraisonAI/issues).