Fcop MCP server

Read from the package source without running it. The installed server may list more.

• _load_events

  Load events from the log, apply optional filters. Returns (filtered, total).

• approve_task

  Approve lifecycle stage: ``review`` → ``done`` (v3 directory move).

• archive_task

  Archive a task after governance acceptance (v3: ``_lifecycle/archive/``; v2: ``log/``).

• archive_to_history

  Deep-history cold storage after governance archive (v3 only).

• bulk_archive_to_history

  Migrate **all** tasks from ``_lifecycle/archive/`` into the deep history archive.

• check_updatewrite action

  Compare the installed fcop-mcp version to the latest on PyPI.

• claim_task

  Claim a task: ``inbox`` → ``active`` (v3 Hot Path start).

• create_branchwrite action

  Create a Branch through Core T1; unavailable family digest is null with reasons.

• create_custom_teamwrite action

  Create an FCoP project with a custom roster of roles.

• create_taskwrite action

  Create a new task and place it in the inbox (v3) or tasks folder (v2).

• deploy_role_templateswrite action

  Deploy the three-layer team documentation into ``shared/``.

• drop_suggestionwrite action

  Pressure valve for agents who disagree with the current FCoP protocol.

• fcop_audit

  **协议体检工具（ADR-0032）** — deep compliance scan, not Hot Path.

• fcop_check

  **FCoP audit.** Cross-reference git working tree + frontmatter against the FCoP ledger.

• fcop_create_alertwrite action

  **ADMIN / Governance Observer only.** Manually file a governance alert.

• fcop_list_alerts

  **ADMIN Governance Alert Inbox.** List governance alerts from fcop/alerts/.

• fcop_report

  **FCoP Rule 0 — first tool call of every new session, also the general project-status report.**

• finish_task

  Move lifecycle stage: ``active`` → ``done`` (v3 directory move only).

• get_available_teams

  List bundled preset teams and their role rosters.

• get_governance_summary

  **FCoP governance summary.** Return aggregate statistics from the governance event log: total calls by risk level, most active tools, and any CRITICAL_TAG events that should be reconciled with Tasks and Reviews.

• get_team_status

  Return a concise status snapshot of the current project.

• init_project

  Initialize an FCoP project with a bundled preset team.

• init_solo

  Initialize an FCoP project in **Solo mode** (one AI, no dispatch).

• inspect_family

  Read a canonical ordered family, precise REPORT heads, readiness and convergence facts.

• inspect_task

  Validate a task file against FCoP grammar (Hot Path pre-flight).

• list_governance_events

  **FCoP governance audit.** Read the append-only governance event log.

• list_history

  List the deep history archive.

• list_issues

  List issues, optionally filtered.

• list_reports

  List reports, optionally filtered.

• list_reviews

  List REVIEW files, optionally filtered.

• list_tasks

  List tasks, optionally filtered.

• list_workspaces

  List all ``workspace/<slug>/`` subdirectories with their metadata.

• mark_human_approved

  Record a human approval decision on a ``needs_human`` REVIEW file.

• merge_branches

  Core atomically materializes the caller's decision. Never chooses a winner or archives Root.

• new_workspacewrite action

  Create a workspace subdirectory under ``workspace/<slug>/``.

• read_history_task

  Read a task from the deep history archive.

• read_report

  Read the full content of a report file.

• read_review

  Read the full content of a REVIEW file.

• read_task

  Read the full content of a task file (Hot Path pre-flight).

• redeploy_rules

  **Legacy v1-v3 only; ADMIN-only.** Re-deploy legacy bundled rules.

• reject_task

  Reject / recall: ``review`` → ``active`` (v3 rework loop).

• reopen_task

  Request only v4 T6 done->active. Actor is audit data, never authority.

• set_project_dir

  Pin the project root for this MCP session.

• submit_taskwrite action

  Submit for review: ``active`` → ``review`` (v3 lifecycle directory move).

• upgrade_fcop

  Return the install-method-specific command to upgrade fcop-mcp.

• validate_team_config

  Dry-run validation for a custom team config.

• write_issuewrite action

  File an issue under ``docs/agents/issues/``.

• write_reportwrite action

  Write a completion report for a task.

• write_reviewwrite action

  Write a REVIEW file (governance-layer decision, per ADR-0017/0025).

• write_taskwrite action

  Create a new task file (Cold Path dispatch or formal intake only).

• Code scan30 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 3 days ago15/15
• Maintainer identityregistry namespace matches repository owner6/10

Safety score

89/100

higher than 83% of 4,461 AI and agents servers

Tools

50

the typical AI and agents server has 6

Tools that change things

26%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

2

more than 65% of 2,713 AI and agents servers

Downloads a week

170

more than 72% of 1,554 AI and agents servers with a package

Grade history

• 2026-10-03restoreC → Ascore 89

Fcop: common questions

Is Fcop MCP server safe?

Yes, by our scan: it is graded A (89/100). Read the Fcop safety report

How do I install Fcop?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Fcop need an API key?

No secret keys are declared. It reads 1 setting from the environment.

Is Fcop maintained?

The last commit was 36 days ago (2026-09-30). The latest release is v4.0.5.

What can I use instead of Fcop?

Servers from other publishers that do the same job: Agent-Native Chat MCP server, Ts Core MCP server and DCC-MCP Core MCP server.

How does Fcop compare with other AI and agents MCP servers?

safety score 89/100 (higher than 83% of 4,461 AI and agents servers); tools 50 (the typical AI and agents server has 6); tools that change things 26% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.