Evidra

Flight recorder and reliability scoring for infrastructure automation

Evidra records intent, outcome, and refusal for every infrastructure mutation — across MCP agents, CI pipelines, A2A agents, and scripts. The append-only evidence chain powers behavioral signal detection and reliability scoring. Canonicalization and risk assessment are optional external enrichments, not required core dependencies.

CLI and MCP are the authoritative analytics surfaces today.

Two ways to use it:

Quick Start — MCP Server

{
  "mcpServers": {
    "evidra": {
      "command": "evidra-mcp",
      "args": ["--evidence-dir", "~/.evidra/evidence"]
    }
  }
}

Your agent gets seven default DevOps tools: run_command, collect_diagnostics, write_file, describe_tool, prescribe_smart, report, and get_event. The normal path is still run_command with automatic evidence recording for mutations. Use describe_tool only when you want the full explicit-control schema for prescribe_smart or report. Add --full-prescribe when you also want artifact-aware prescribe_full.

Quick Start — CLI (No MCP)

# Wrap any command — evidence recorded automatically
evidra record -f deploy.yaml -- kubectl apply -f deploy.yaml

# Import from CI pipelines
evidra import --input record.json

# View reliability scorecard
evidra scorecard --period 30d

Works with any agent framework, CI system, or script. No MCP required.

Security boundary: Evidra does not sandbox the wrapped command. Treat it with the same trust model as direct shell execution.

# Install
brew install samebits/tap/evidra

What Your Agent Gets

Smart output — fewer tokens, same information

Agent: run_command("kubectl get deployment web -n demo")

# Without evidra-mcp (raw JSON): ~2,400 tokens
{"apiVersion":"apps/v1","metadata":{"managedFields":[...],...},"spec":{...},"status":{...}}

# With evidra-mcp (smart output): ~40 tokens
deployment/web (demo): 0/2 ready | image: nginx:99.99 | Available=False

Auto-evidence for mutations — zero agent code

Agent: run_command("kubectl apply -f fix.yaml")
  → evidra auto-prescribes (intent recorded)
  → kubectl executes
  → evidra auto-reports (outcome recorded)
  → smart output returned to agent

Read-only commands (get, describe, logs) execute directly — no overhead.

Skills

Install the Evidra skill to give your agent operational discipline: diagnosis before fix, safety boundaries, domain-specific patterns.

7 default tools, plus optional Full Prescribe

Enable --full-prescribe to add Full Prescribe when your agent has artifact bytes and you want artifact-aware explicit intent capture.

Most agents only need run_command. Use collect_diagnostics when the model would otherwise spend multiple turns on get / describe / events / logs. Use write_file for agent-authored manifests or Terraform snippets without leaving the MCP surface. Use describe_tool only when you deliberately want the explicit prescribe_smart / report flow instead of the default auto-evidence path.

Why Not Just kubectl-mcp-server?

For Platform Teams

Self-hosted analytics

docker compose up --build -d

Centralize evidence across agents, pipelines, and controllers:

• Which agents retry the same operation?
• Which scenarios cause the most failures?
• How does model X compare to model Y on real infrastructure?

CI/CD integration

# Wrap any command — CLI records prescribe/execute/report
evidra record -f deploy.yaml -- kubectl apply -f deploy.yaml

# Import completed operations
evidra import --input record.json

# View reliability scorecard
evidra scorecard --period 30d

References: Self-hosted setup · CLI reference · API reference

Intelligence Layer

From the evidence chain, Evidra computes:

• Behavioral signals — protocol violations, retry loops, blast radius, drift detection
• Reliability scorecards — 0-100 score with band and confidence

Risk assessment can be supplied by an external scanner or policy engine as an optional assessment block on prescribe entries. When no assessment is supplied, Evidra still records the intent and outcome and leaves risk fields empty.

Eight behavioral signals documented in the Signal specification.

Explicit Protocol (Advanced)

For agents that want full control over evidence recording:

prescribe_smart / prescribe_full  →  record declared intent (+ optional canonical_action/assessment)
execute    →  run the command (or decline to act)
report     →  record verdict, exit code, or refusal reason

Three evidence modes:

Most users should use Proxy Observed or the default DevOps surface. Smart Prescribe and Full Prescribe are for teams that want explicit prescribe/report control. If an agent needs risk context before executing, run a scanner or policy engine first and include its result as optional assessment enrichment.

Proxy Mode — Wrap Mutation-Oriented MCP Servers

Add evidence to an existing MCP server — zero agent changes:

{
  "mcpServers": {
    "infra": {
      "command": "evidra-mcp",
      "args": ["--proxy", "--", "npx", "-y", "@anthropic/mcp-server-kubernetes"]
    }
  }
}

The proxy records evidence when it sees run_command or other mutation-shaped MCP tool calls it can classify heuristically. Unclassified or read-only tool calls pass through without evidence.

Docs

• MCP Setup Guide
• Skill Setup Guide
• CLI Reference
• API Reference
• Architecture
• Protocol Specification
• Scoring Rationale
• MCP Registry Publication Guide
• Supported Tools

Development

make build
make test
make lint
make test-mcp-inspector    # MCP protocol compliance tests

Environment Variables

License

Licensed under the Apache License 2.0.