Repository Issue Activity (beta)

#17 Support MCP server prompts

#748 docs: openai.base_url /v1 vs MCP_API_BASE_URL for hosted Chat Completions hosts

#209 Configurable max tool response size

#693 Feature: Add trust verification for MCP servers before orchestration

#745 Add an official HOL Guard pre-tool security example

#692 Add TheCrawler as example MCP tool — web extraction with structured errors

#730 Architecture: Preventing Context Drift in MCP Agents with Temporal Signatures

#654 Add governance layer for agent tool calls and decisions

#683 Integration Proposal: CAJAL Scientific Paper Generator as MCP Agent

#679 Curious — once agents start executing actions (APIs, workflows, etc.), how are you handling the decision point before execution?

#640 [Question] Reliability patterns under noisy conditions

#644 Feature Suggestion: Lightning wallet MCP for autonomous agent payments

#655 Resource: Clarvia AEO Scanner — measure MCP server quality for agents using mcp-agent

#656 AEO Score: 35/100 — AI agent discoverability for mcp-agent

#670 deploy command executes arbitrary user code by importing project main.py in-process

#671 get_capabilities_task silently returns exception objects in ServerCapabilities dict under partial server failure

#669 Live API key printed in plain text to terminal on deploy

#673 Agent identity for cross-org orchestration workflows

#718 idea for rust wasm

#667 Support OAuth Dynamic Client Registration (DCR) for traditional OAuth Providers

#713 feat: Add persistent memory example using Dakera MCP — addresses long-term memory gap (#12)

#658 [RFC] Cryptographic agent identity for MCP agents via WTRMRK — who is this agent?

#657 Security Vulnerability Report - Awaiting Acknowledgment

#381 Duplicate evaluator's instruction in evaluator prompt

#25 content in OpenAI ChatCompletion messages is a list, not string