# edm_project

Project an EDM artifact into the canonical agent-consumable shape (ADR-0009). Returns governance-preserving projection with optional LLM-generated context note.

Agent View of the PolicyLayer registry record for `edm_project`. HTML page: https://policylayer.com/tools/deepadata-edm/edm-project

## Facts

- Tool: `edm_project`
- Server: Deepadata Edm (`deepadata-edm-mcp-server`) — https://policylayer.com/tools/deepadata-edm.md
- Install: `npx -y deepadata-edm-mcp-server`
- Homepage: https://www.npmjs.com/package/deepadata-edm-mcp-server
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `artifact_id` | string | yes | The artifact ID to project |
| `context_note` | boolean | no | Generate a 2-3 sentence LLM summary for context injection (default: false) |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "edm_project",
    "arguments": {
      "artifact_id": "<artifact_id>"
    }
  }
}
```

## Why edm_project is rated Low

This tool retrieves and transforms EDM artifacts for consumption by agents without modifying the underlying data or causing side effects. The projection operation is a read-like transformation that reshapes existing data into a different format. No create, delete, execute, or financial operations are described.

From the tool's own definition: "Tool description states it 'Project[s] an EDM artifact into the canonical agent-consumable shape' and 'Returns governance-preserving projection with optional LLM-generated context note.' The verbs 'project' and 'returns' indicate data retrieval and…"

## Use case

AI agents call edm_project to retrieve information from Deepadata Edm without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Deepadata Edm:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "edm_project": {}
  }
}
```

## Other tools on Deepadata Edm (8)

- `deepadata_activate` — Read — https://policylayer.com/tools/deepadata-edm/deepadata-activate.md
- `deepadata_activate_reason` — Read — https://policylayer.com/tools/deepadata-edm/deepadata-activate-reason.md
- `edm_wiki_lint` — Read — https://policylayer.com/tools/deepadata-edm/edm-wiki-lint.md
- `edm_wiki_search` — Read — https://policylayer.com/tools/deepadata-edm/edm-wiki-search.md
- `extract_from_content` — Read — https://policylayer.com/tools/deepadata-edm/extract-from-content.md
- `validate_edm` — Read — https://policylayer.com/tools/deepadata-edm/validate-edm.md
- `edm_wiki_generate` — Write — https://policylayer.com/tools/deepadata-edm/edm-wiki-generate.md
- `seal_artifact` — Write — https://policylayer.com/tools/deepadata-edm/seal-artifact.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=deepadata-edm · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deepadata-edm