Is io.github.recourseOS/recourse safe to use?

io.github.recourseOS/recourse has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.recourseOS/recourse?

io.github.recourseOS/recourse supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.recourseOS/recourse do?

io.github.recourseOS/recourse provides 5 tools: recourse_evaluate_terraform, recourse_evaluate_shell, recourse_evaluate_mcp_call, recourse_evaluate_with_evidence, recourse_supported_resources. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.recourseOS/recourse?

io.github.recourseOS/recourse is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.recourseOS/recourse actively maintained?

io.github.recourseOS/recourse is actively maintained — last commit was 25 days ago. It has 1 GitHub stars.

io.github.recourseOS/recourse

recourse-cli

Consequence evaluation for AI agents. Check recoverability before destructive actions.

1 68/wk 5 tools GitHub npm

No known CVEs

No license

Actively maintained

Last commit 25d ago

Works with most clients

Transport: stdio, sse, http

5 tools

Grade F

Edit this pageView history

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "recourseos": {
      "args": [
        "-y",
        "recourse-cli@latest",
        "mcp",
        "serve"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-recourseos-recourse)](https://mcppedia.org/s/io-github-recourseos-recourse)

Read me

What io.github.recourseOS/recourse does

Recourse is an MCP server that evaluates Terraform plans, shell commands, and tool calls before execution. It returns structured facts — recoverability tier, evidence assessment, and risk level — so callers can make context-aware decisions. Agents call Recourse before they act; humans see what the agent checked.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y 'recourse-cli' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

54/100across 5 weighted dimensions

How we score →

0255075100

−46

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked recourse-cli against OSV.dev.

Inventory

Tools (5)

Click any tool to inspect its schema.

Inventory

Resources (1)

recourse://instructions

Safety protocol — when to call, how to interpret results

recourse://instructions

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.recourseOS/recourse safe to use?: io.github.recourseOS/recourse has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.recourseOS/recourse?: io.github.recourseOS/recourse supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.recourseOS/recourse do?: io.github.recourseOS/recourse provides 5 tools: recourse_evaluate_terraform, recourse_evaluate_shell, recourse_evaluate_mcp_call, recourse_evaluate_with_evidence, recourse_supported_resources. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.recourseOS/recourse?: io.github.recourseOS/recourse is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.recourseOS/recourse actively maintained?: io.github.recourseOS/recourse is actively maintained — last commit was 25 days ago. It has 1 GitHub stars.

Similar servers

Others in ai-ml

View all →

Sequential Thinking MCP Server96

Dynamic problem-solving through sequential thought chains

87.8k 1

Antigravity Workspace Template96

Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.

1.3k 2

Memory MCP Server96

Persistent memory using a knowledge graph

87.8k 5

Context Mode95

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

18.3k 6

MCP Security Weekly

Get CVE alerts and security updates for io.github.recourseOS/recourse and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "recourseos": {
      "args": [
        "-y",
        "recourse-cli@latest",
        "mcp",
        "serve"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-recourseos-recourse)](https://mcppedia.org/s/io-github-recourseos-recourse)

Read me

What io.github.recourseOS/recourse does

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y 'recourse-cli' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

README

RecourseOS

Consequence layer for AI agents
Check recoverability before destructive actions

[![SafeSkill 83/100](https://img.shields.io/badge/SafeSkill-83%2F100_Passes%20with%20Notes-yellow)](https://safeskill.dev/scan/recourseos-recourse)

Website · MCP Setup · Console · Coverage

Add to Your Agent

One config block. Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.

{
  "mcpServers": {
    "recourseos": {
      "command": "npx",
      "args": ["-y", "recourse-cli@latest", "mcp", "serve"]
    }
  }
}

The server exposes five tools:

Tool	Purpose
`recourse_evaluate_terraform`	Check Terraform plans before `terraform apply`
`recourse_evaluate_shell`	Check shell commands before execution
`recourse_evaluate_mcp_call`	Check other MCP tool calls before invocation
`recourse_evaluate_with_evidence`	Re-evaluate with verification evidence
`recourse_supported_resources`	List resources with deterministic rules

Plus a resource agents can read:

Resource	Purpose
`recourse://instructions`	Safety protocol — when to call, how to interpret results

Each tool returns:

riskAssessment: engine's summary read — allow, warn, escalate, or block
recoverability: tier and reasoning for each mutation
evidence: what was found, what's missing, what's needed for confident classification
crossActionRisks: dangerous patterns where individual actions are safe but their combination is unrecoverable (e.g., deleting a backup + the database it backs up)

The engine emits facts. Callers interpret them in context — a block assessment in staging might be acceptable; in production it might require approval.

What Agents Get

Terraform plan says:

- aws_db_instance.main will be destroyed

Recourse tells the agent what that means:

aws_db_instance.main
recoverability: unrecoverable
reason: skip_final_snapshot=true, backup_retention_period=0, deletion_protection=false
riskAssessment: block

The agent can interpret these facts: "Recourse assessed this as block-level risk — deletes the database with no backup. Should I proceed?"

That's different from "I deleted your production database."

Agent Instructions

Agents can read the built-in safety protocol from recourse://instructions. Or use this prompt:

Before executing destructive operations, call RecourseOS:
- Shell commands → recourse_evaluate_shell
- Terraform plans → recourse_evaluate_terraform
- Other MCP tools →

... [View full README on GitHub](https://github.com/recourseos/recourse#readme)

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

54/100across 5 weighted dimensions

How we score →

0255075100

−46

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked recourse-cli against OSV.dev.

Inventory

Tools (5)

Click any tool to inspect its schema.

Inventory

Resources (1)

recourse://instructions

Safety protocol — when to call, how to interpret results

recourse://instructions

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.recourseOS/recourse safe to use?: io.github.recourseOS/recourse has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.recourseOS/recourse?: io.github.recourseOS/recourse supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.recourseOS/recourse do?: io.github.recourseOS/recourse provides 5 tools: recourse_evaluate_terraform, recourse_evaluate_shell, recourse_evaluate_mcp_call, recourse_evaluate_with_evidence, recourse_supported_resources. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.recourseOS/recourse?: io.github.recourseOS/recourse is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.recourseOS/recourse actively maintained?: io.github.recourseOS/recourse is actively maintained — last commit was 25 days ago. It has 1 GitHub stars.

Similar servers

Others in ai-ml

View all →

Sequential Thinking MCP Server96

Dynamic problem-solving through sequential thought chains

87.8k 1

Antigravity Workspace Template96

Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.

1.3k 2

Memory MCP Server96

Persistent memory using a knowledge graph

87.8k 5

Context Mode95

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

18.3k 6

MCP Security Weekly

Get CVE alerts and security updates for io.github.recourseOS/recourse and similar servers.

Community