Claude Code connects to Provely through the MCP server, the CLI, the REST API. The agent does the action. Provely verifies the outcome and signs a receipt. Claude Code never holds the verifier credentials.

A person verified the Claude Code capabilities on 2026-09-05. Agent products change monthly. Re-verify before you build.

Source: integration profile claude-code · retrieved 2026-09-05

Which surfaces does Claude Code use?

SurfaceSupportDetail
MCP serverSupportedtransport stdio, http; config .mcp.json
CLISupportedRuns through the shell tool of the agent.
SDKNot supported
REST APISupportedAny HTTP call reaches the control plane.

Which guidance files does Claude Code read?

The renderer writes Agent Skills SKILL.md, CLAUDE.md fragment from one source. A new agent needs a profile, not core code.

FormatPathMode
Agent Skills SKILL.md.claude/skills/provely-outcome-verification/SKILL.mdwrite
CLAUDE.md fragmentCLAUDE.mdappend
Claude Code hook settings.provely/hooks/claude-settings.mdfragment
CI gate workflow.provely/ci/github-actions.ymlfragment

How is a false completion claim blocked?

EnforcementSupportDetail
Advisory guidanceSupportedThe instruction files state the rules for every agent.
Lifecycle hooksSupportedPostToolUse, Stop
CI gateSupportedprovely verify --wait fails the pipeline unless the verdict is VERIFIED.

How do I connect Claude Code?

Connect Claude Code to Provely

  1. Install the CLI.Run npx provely --version, or download the static binary.
  2. Register the MCP server.Add the Provely server to .mcp.json. Use provely mcp for stdio, or the hosted HTTP server with a bearer token. The tools are begin, verify, status, and receipt.
  3. Write the guidance files.Run provely init --agent claude-code. It writes .claude/skills/provely-outcome-verification/SKILL.md (write), CLAUDE.md (append), .provely/hooks/claude-settings.md (fragment), .provely/ci/github-actions.yml (fragment). The guidance carries one rule: a successful tool call is not completion.
  4. Install the hooks.Enable the PostToolUse, Stop hooks. A hook calls the CLI and blocks a completion claim while an operation is PENDING.
  5. Add the CI gate.Run provely verify --wait <duration> in the pipeline. The step fails unless the verdict is VERIFIED. Exit codes: 0 VERIFIED, 2 PENDING, 3 FAILED, 4 CONTRADICTED, 5 UNVERIFIABLE.
  6. Report the verdict exactly as returned.VERIFIED: "The action is verified complete. Receipt: <id>." PENDING: "The action is accepted but not yet verified. Operation: <id>."

What else does the profile state?

  • Verified 2026-09-05: hook events PostToolUse and Stop; exit 2 blocks a Stop and returns stderr to the agent; PostToolUse returns hookSpecificOutput.additionalContext. Source: https://code.claude.com/docs/en/hooks.
  • Verified 2026-09-05: hooks live in .claude/settings.json, .claude/settings.local.json, or ~/.claude/settings.json. The Stop input carries stop_hook_active. Claude Code ends the turn after 8 consecutive blocks. Source: https://code.claude.com/docs/en/hooks.md.
  • Verified 2026-09-05: skills live in .claude/skills/<name>/SKILL.md and MCP servers in .mcp.json. Source: https://code.claude.com/docs/en (skills, mcp).
  • Register the two hook scripts with the snippet in .provely/hooks/claude-settings.md. The Stop hook calls provely status --open --json. While that flag does not exist (request I2), the hooks exit 0 and print a systemMessage that says enforcement is off.
  • The hooks see only operations that called begin. An action that never opened an operation is invisible to them. The scanner and the CI gate cover that case.
  • Headless runs (claude -p) use the CI gate in .provely/ci/github-actions.yml like every other pipeline.

Claude Code keeps its action credentials, and no surface returns the verifier credentials to it. Read the credential boundary. An operation outlives the session that opened it. Read the API reference.

Which host versions does the profile cover?

>=2.0.0. The integrations team last verified the profile with 2.1.261 on 2026-09-05 (npm @anthropic-ai/claude-code; CHANGELOG.md).