// SCAN REPORT

Code Context

97 tools. 43 can modify or destroy data without limits.

6 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

43 can modify or destroy data

54 read-only

97 tools total

Community server · catalogue entry verified 29/06/2026

How to control Code Context ↓

TOOL MAP

What Code Context exposes to your agents

Read (54) Write / Execute (37) Destructive / Financial (6)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Code Context tools

Destructive · Critical triage_retro_finding Triage an open try_next retro finding at sprint planning: adopt it as a ticket, drop it with a reason, or defer it to the next planning. The Destructive · High remove_dependency Remove a dependency between two tickets Destructive · High remove_tag Remove a tag from a ticket Destructive · High reset_agents Reset all agents to factory defaults. WARNING: This deletes all current agents and re-seeds from TypeScript defaults.

43 of Code Context's 97 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Code Context

PolicyLayer is an MCP gateway — it sits between your AI agents and Code Context, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "remove_dependency": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_dependency": {
    "limits": [
      {
        "counter": "add_dependency_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "acknowledge_ticket_changes": {
    "limits": [
      {
        "counter": "acknowledge_ticket_changes_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Code Context — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CODE CONTEXT →

Instant setup, no code required.

FULL CATALOGUE

All 97 Code Context tools

DESTRUCTIVE 6 tools

Destructive remove_dependency Remove a dependency between two tickets Destructive remove_tag Remove a tag from a ticket Destructive reset_agents Reset all agents to factory defaults. WARNING: This deletes all current agents and re-seeds from TypeScript de Destructive reset_skills Reset all skills to factory defaults. WARNING: This deletes all current skills and re-seeds from TypeScript de Destructive reset_sprint_process Reset sprint process configuration to factory defaults. Destructive triage_retro_finding Triage an open try_next retro finding at sprint planning: adopt it as a ticket, drop it with a reason, or defe

EXECUTE 4 tools

Execute execute Run an INSERT, UPDATE, or DELETE against the context database Execute index_directory Scan a directory, parse all files, extract metadata/exports and build a dependency graph. Use freshness_check= Execute run_onboarding Run the full project onboarding sequence — checks and fixes all missing setup steps Execute start_sprint Create a sprint with tickets in one call. Creates the sprint, creates tickets from provided list, assigns agen

WRITE 33 tools

Write add_dependency Add a dependency between two tickets (blocks, blocked_by, or related) Write add_retro_finding Add a retrospective finding to a sprint Write add_tag Add a tag to a ticket (creates tag if it doesn Write create_blocker Report a blocker on a sprint Write create_discovery Log a finding from a discovery sprint Write create_epic Create a new epic to group related tickets Write create_milestone Create a new milestone for the product roadmap Write create_sprint Create a new sprint Write create_ticket Create a new ticket in a sprint Write export_sprint_report Generate a complete markdown sprint report Write export_to_file Export database to a JSON file on disk Write generate_vision_animation Generate project vision animation data (JSON) and provide the Remotion render command Write handle_run_kickoff Handle the /kickoff ceremony triggered from the dashboard. Initiates the full project lifecycle from vision th Write handle_run_retro Handle the retrospective ceremony triggered from the dashboard. Runs retro for the specified sprint. Write handle_run_review Handle the sprint review ceremony triggered from the dashboard. Shows sprint completion summary and demo. Write import_from_file Restore database from a JSON dump file on disk Write plan_sprint Create a new sprint and assign tickets to it in one operation Write resolve_blocker Mark a blocker as resolved Write restore_database Restore database from a JSON dump. Wraps in transaction for safety. Write send_claude_output Stream Claude Write send_claude_step Notify the dashboard wizard about a step transition during a ceremony. Shows step status in the output stream Write send_step_progress Send real-time step progress updates to the wizard modal. Shows which step Claude is executing and current pro Write set_change_reason Set a reason/explanation for a recorded file change Write set_description Set a manual description for a file (persists across re-indexes) Write set_directory_description Set a manual description for a directory (persists across re-indexes) Write update_discovery Update a discovery Write update_epic Update an existing epic Write update_milestone Update a milestone Write update_skill_sets Enable or disable predefined skill sets (frontend fe:, landing la:, workflow wf:) for this project. Partial up Write update_sprint Update sprint status or details Write update_sprint_config Create or update the SPRINT_PROCESS skill — stores sprint process configuration in the database Write update_ticket Update a ticket Write update_vision Create or update the PRODUCT_VISION skill content

READ 54 tools

Read acknowledge_ticket_changes Acknowledge board-edited tickets after reacting to their changes: clears pending_change flags and completes th Read advance_sprint Advance sprint to the next phase. Checks all gates, advances if they pass, returns summary + next actions. If Read analyze_retro_patterns Analyze retrospective findings across all sprints — category breakdown, recurring issues, and action follow-th Read dump_database Export the entire database to JSON for backup/restore Read find_symbol Find which file(s) export a given function, component, type, or constant Read get_agent Get full details of a scrum agent by role Read get_audit_trail Get audit trail for an entity — all state changes over time Read get_backlog List all backlog tickets — unassigned to any sprint or carried over from closed sprints Read get_burndown Get burndown data for a sprint — daily snapshots of remaining vs completed points Read get_changes Get recent file changes grouped by file path, showing what changed (size, lines, exports, summary diffs) Read get_dependency_graph Get all dependencies for a ticket or sprint Read get_discovery_coverage Get coverage report for a discovery sprint — auto-promotes planned discoveries whose linked ticket is DONE Read get_file_context Get a file Read get_mood_trends Get mood history for an agent or all agents — detects burnout patterns Read get_onboarding_status Check project setup status and return what is configured vs missing Read get_project_status Check if the project is properly set up and return health status Read get_resume_state Single-call resume detection. Returns minimal structured data (~150 tokens) for all command Step 0 flows. Repl Read get_skill Fetch the full content of a single skill by name (e.g. Read get_sprint Get full sprint details with tickets, bugs, blockers, and retro findings Read get_sprint_config Read the SPRINT_PROCESS skill from the database — returns the current sprint process configuration Read get_sprint_instructions Get sprint process instructions — lifecycle, ticket workflow, retro rules, role responsibilities, and close ch Read get_sprint_playbook Get the current sprint playbook: phase, ticket summary, gate status, blockers, and directive next actions. Fol Read get_sprint_summary Get a one-line summary per sprint — name, status, velocity, ticket progress. Ultra-compact for quick overviews Read get_ticket Get full ticket details with subtasks and linked bugs Read get_time_report Get time tracking report for a sprint — estimated vs actual hours per agent Read get_token_usage Get token usage history, optionally filtered by sprint or ticket Read get_user_response Poll for the user Read get_velocity_trends Get velocity trend data across sprints — committed vs completed, completion rate, bugs Read health Check server health and connectivity Read link_discovery_to_ticket Link a discovery finding to its implementation ticket — auto-sets status to planned (or implemented if ticket Read link_ticket_to_epic Link a ticket to an epic, or unlink by passing null epic_id Read link_ticket_to_milestone Link a ticket to a milestone by setting its milestone_id Read list_agents List all scrum team agents with their roles and capabilities Read list_decisions List logged decisions with optional category filter Read list_discoveries List discovery findings with optional filters. Compact by default (open items, truncated one-liners) — pass ve Read list_epics List epics with optional status and milestone filters, including ticket progress counts. Use compact=true for Read list_recent_events List recent events from the audit trail — use this to detect dashboard-initiated changes (e.g. user moved a ti Read list_retro_findings List retrospective findings with optional filters Read list_sprints List all sprints with status and ticket counts. Use compact=true for minimal output (id, name, status only) to Read list_tickets List tickets with optional filters. Use compact=true for minimal output (id, title, status) to save tokens. Read load_phase_context Single-call phase context loader. Bundles all data needed for a specific workflow phase into one response, rep Read log_bug Log a bug against a sprint Read log_decision Log an architectural or process decision with rationale and alternatives considered Read log_event Manually log an event in the audit trail Read log_time Log estimated or actual hours on a ticket Read log_token_usage Record token usage for a session/task. Use at the end of a task to track real consumption for benchmarking. Read query Run a read-only SELECT query against the context database Read record_mood Record an agent Read request_user_input Request user input via the dashboard wizard modal. Writes a question to the bridge action queue. If the dashbo Read search_files Search indexed files by path or summary (supports % wildcards) Read search_scrum Full-text search across tickets, retro findings, blockers, and bugs Read snapshot_sprint_metrics Capture a daily burndown snapshot for a sprint — records remaining, completed, added, and removed points Read sync_scrum_data Re-seed scrum data from factory defaults (agents + skills). Does not overwrite existing data — only fills empt

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Code Context

Can an AI agent delete data through the Code Context MCP server? +

Yes. The Code Context server exposes 6 destructive tools including remove_dependency, remove_tag, reset_agents. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Code Context? +

The Code Context server has 33 write tools including add_dependency, add_retro_finding, add_tag. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Code Context.

How many tools does the Code Context MCP server expose? +

97 tools across 4 categories: Destructive, Execute, Read, Write. 54 are read-only. 43 can modify, create, or delete data.

How do I enforce a policy on Code Context? +

Register the Code Context MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Code Context tool call.

Deterministic rules across all 97 Code Context tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CODE CONTEXT →

Instant setup, no code required.

97 Code Context tools catalogued and risk-classified — across an index of 43,000+ MCP servers.