portofcontext/pctx
pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.
This is an execution layer that helps AI agents interact with various tools and services more efficiently. It takes agent requests and converts them into executable code that runs securely, significantly reducing the amount of back-and-forth communication an agent needs for complex tasks. AI developers who build and deploy AI agents that need to integrate with external systems will find this useful.
212 stars.
Use this if you are building AI agents and want a more efficient, secure, and unified way for them to interact with multiple external tools and services.
Not ideal if you are a non-developer end-user looking for a ready-to-use AI application, as this is a developer framework.
Stars
212
Forks
23
Language
Rust
License
MIT
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/portofcontext/pctx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AndrewAltimit/template-repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows,...
knowledgepa3/gia-mcp-server
MCP proxy for GIA Governance — connects Claude Desktop and Claude Code to the hosted GIA...
Chimera-Protocol/csl-core
Deterministic safety layer for AI agents. Z3-verified policy enforcement.
agentralabs/agentic-contract
Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation...
postralai/masquerade
The Privacy Firewall for LLMs