Codacy for AI agents

Codacy automates code review, tracking code quality and technical debt across a codebase so a team can enforce standards without manual review of every line. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Developer toolsAPI keyMCP + RESTcodacy.com
AUDIT LOG · CODACYPOLICY: acme-support
09:41:07 · claude · u_8f2read
codacy.list_tools
List Tools✓ allowed · 212ms
09:41:08 · claude · u_8f2read
codacy.get_health
Get Health✓ allowed · 164ms
09:41:09 · claude · u_8f2write
codacy.create_api_token
Create API Token✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
codacy.delete_api_token
Delete API Token✕ blocked · policy: deny
EVERY CODACY CALL, ON THE RECORD
01 · USE CASES

What agents do in Codacy.

01

Check a repository's quality metrics

Check a repository's code quality settings before deciding whether to adjust its rules.

02

List flagged issues by tool

List which analysis tools are enabled for a repository before adding a new one.

03

Check organization access

Check which organizations a user has access to before connecting a new repository.

02 · ACTIONS

18 Codacy actions, graded by risk.

Every Codacy action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

16

Look things up. Allowed by default.

  • codacy.get_health
    Get Health
  • codacy.list_tools
    List Tools
  • codacy.get_version
    Get Version
  • codacy.list_projects
    List Projects
  • codacy.get_tool_pattern
    Get Tool Pattern
  • codacy.list_metrics_tools
    List Metrics Tools
  • codacy.get_account_details
    Get Account Details
  • codacy.list_tools_patterns
    List Tools Patterns
  • codacy.list_languages_tools
    List Languages and Tools
  • codacy.get_user_organizations
    Get User Organizations
  • codacy.list_duplication_tools
    List Duplication Tools
  • codacy.list_login_integrations
    List Login Integrations
  • codacy.get_configuration_status
    Get Configuration Status
  • codacy.list_provider_integrations
    List Provider Integrations
  • codacy.list_analysis_organizations_repositories
    List Analysis Organizations Repositories
  • codacy.get_organizations_repositories_settings_languages
    Get Organizations Repositories Settings Languages

write

1

Create and change things. Allow, or ask the user first.

  • codacy.create_api_token
    Create API Token

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • codacy.delete_api_token
    Delete API Token
03 · HOW IT WORKS

Codacy in three steps.

  1. 01Your users connect CodacyThey add their Codacy api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create API Token” can wait for the user, and “delete API Token” can be denied outright.
  3. 03Any agent can actYour agent calls Codacy through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('codacy', {
  read: 'allow',
  write: 'ask',        // create_api_token
  destructive: 'deny',  // delete_api_token
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Codacy connects.

Users add their Codacy api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Codacy connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Codacy from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Codacy and Arc0, answered.

Q01

Can I use Codacy with Claude, ChatGPT or Cursor?

Yes. Connect Codacy to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Codacy actions you allow.

Q02

How do users connect Codacy?

Users add their Codacy api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Codacy actions can my agent take?

18 in total: 16 read, 1 write and 1 destructive, such as “create API Token”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Codacy?

Yes. Actions like “delete API Token” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Codacy too?

Yes. The same Codacy connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Codacy into your agent.

Your users connect Codacy once, under your brand. Your agent gets 18 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan