# mcp-tacit

> Use this tool when you need to ensure safe and controlled interactions between AI agents and external tools, solving problems of capability escalation, budget overruns, and information leakage. The mcp-tacit tool provides a Scala 3 interface with capture checking, tracking agent capabilities and enforcing access rights and budgets. It is ideal for use cases requiring robust safety guarantees, such as secure multi-agent systems and sensitive data processing.

Canonical page: https://skillsregistry.net/skills/lampepfl-tacit  
JSON: https://api.skillsregistry.net/v1/skills/lampepfl-tacit

## Description

TACIT (Tracked Agent Capabilities In Types) is a safety harness for AI agents. Instead of calling tools directly, agents write code in Scala 3 with capture checking: a type system that statically tracks capabilities and enforces that agent code cannot forge access rights, cannot perform effects beyond its budget, and cannot leak information from pure sub-computations. It provides an MCP interface,

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/be3ux50ejp)
- **Repository:** <https://github.com/lampepfl/tacit>

## 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": "lampepfl-tacit"
    }
  }
}
```

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