# pctx

> pctx — portofcontext-pctx. Use this tool when you need to execute agentic tool calls securely and efficiently. It solves problems related to token-efficient workflows by auto-converting tools and servers into sandboxed code, accepting inputs from git and other sources, and producing secure executable outputs. Ideal for use cases requiring secure and efficient execution of agent tools and MCP servers.

Canonical page: https://skillsregistry.net/skills/portofcontext-pctx  
JSON: https://api.skillsregistry.net/v1/skills/portofcontext-pctx

## Description

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.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-24

## Source

- **Source listing:** [GitHub](https://github.com/portofcontext/pctx)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "portofcontext-pctx"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/portofcontext-pctx` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/portofcontext-pctx/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt