// SCAN REPORT

Codevira MCP

48 tools. 20 can modify or destroy data without limits.

20 write tools that can modify data. Rate limits recommended.

Last updated: 12 Jun 2026

20 can modify or destroy data

28 read-only

48 tools total

Community server · catalogue entry verified 12/06/2026

How to control Codevira MCP ↓

TOOL MAP

What Codevira MCP exposes to your agents

Read (28) Write / Execute (20) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Codevira MCP tools

Write · Medium bulk_import_phases This tool creates or modifies phase records in bulk, which is characteristic of Write operations. Write · Medium add_phase This tool creates new data (a phase) in a shared knowledge base used across sessions. Write · Low apply_skill_outcome This tool creates or modifies skill outcome data within a shared knowledge base, which is a reversible write operation. Write · Medium complete_phase This tool creates or modifies data (phase completion state) in a persistent knowledge base, which is reversible (a phase could be re-opened or reset).

20 of Codevira MCP's 48 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Codevira MCP

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

Rate limit write operations

{
  "consensus_propose_supersession": {
    "limits": [
      {
        "counter": "consensus_propose_supersession_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "reflect": {
    "limits": [
      {
        "counter": "reflect_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 Codevira MCP — 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 CODEVIRA →

Free to start. No card required.

FULL CATALOGUE

All 48 Codevira MCP tools

WRITE 20 tools

Write consensus_propose_supersession v3.1.0 M7 Phase C: Open a cross-IDE supersession proposal. Write defer_phase Move an upcoming phase to the deferred list. Write reaffirm_decision v3.2.0: refresh a do_not_revert decision Write record_skill v3.1.0 M3: Author a new skill in the canonical store Write refresh_graph Auto-generate context graph nodes for new or unregistered files. Write supersede_decision v2.1.2 Item 26: retire old_id and link to a replacement. Write supersede_skill v3.1.0 M3: Version a skill. Writes a new skill that supersedes Write add_phase Add a new upcoming phase to the roadmap. Write apply_skill_outcome v3.1.0 M3: Manually record one outcome for a skill — success Write bulk_import_phases v2.1.2 Item 29: backfill multiple historical phases at once. Write complete_phase Mark the current phase as complete and advance to the next upcoming phase. Write consensus_resolve v3.1.0 M7 Phase C: Approve, reject, or withdraw a pending Write promote_skill_to_playbook v3.1.0 M3: Write the skill Write record_decision Record one architectural decision. Set do_not_revert=true to Write set_decision_flag v3.0.0 lightweight flag/tag update for an existing decision. Write update_next_action Update the roadmap Write update_phase_status Update the current phase status: pending | in_progress | blocked. Write working_add v3.1.0 M2: Append one observation or goal to working memory Write working_promote v3.1.0 M2: Promote a working-memory entry to long-term memory Write write_session_log Write a structured session log to .agents/logs/YYYY-MM-DD/.

READ 28 tools

Read reflect v3.1.0 M8: Build the source context + rendered prompt for an Read check_conflict Check whether a proposed decision contradicts any Read consensus_check v3.1.0 M6 Phase B: Scan decisions written since this IDE Read consensus_status v3.1.0 M6: Return the count of pending cross-IDE conflicts + Read get_code Get the full source of a single function or class by name. Read get_history Get recent decisions touching a file. Default: 5 with truncated context Read get_impact Get the blast radius for a file before modifying it. Read get_node Get the context graph node for a file. Returns a SUMMARY by default Read get_phase Get full details of any phase by number — completed, current, or upcoming. Read get_playbook Get curated architectural rules for a specific task type. Read get_reflections v3.1.0 M8: Top-K most recent reflections (newest first). Read get_roadmap Get current project state: phase number, name, status, next action, Read get_session_context Single Read get_signature Get the skeleton of a Python file — all public function and class names, Read get_skill v3.1.0 M3: Composite-ranked search over active skills. Read get_working_context v3.1.0 M2: Compact markdown rendering of the top working-memory Read list_decisions v2.1.2 Item 11: enumerate decisions with filters (since_date, Read list_reflections v3.1.0 M8: Filtered reflection list. Read list_skills v3.1.0 M3: Filtered list of skills. status= Read origin_of v3.1.0 M7: Return the M1 origin block attached to a decision Read query_graph Query the function-level call graph. Find callers, callees, tests, or dependents Read search_decisions Search past decisions across sessions and roadmap phases Read spatial_affordances v3.1.0 M4: Return the affordance keys (task_types) applicable Read spatial_heat v3.1.0 M4: Top-K most-touched files in a time window by Read spatial_nearby v3.1.0 M4: Files topologically near a given file, ranked by Read spatial_neighborhood v3.1.0 M4: Return the neighborhood id + members for a file. Read working_get v3.1.0 M2: Top-K live working-memory entries by decay score

EXPLORE

Related servers

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

FAQ

Questions about Codevira MCP

How do I prevent bulk modifications through Codevira MCP? +

The Codevira MCP server has 20 write tools including consensus_propose_supersession, defer_phase, reaffirm_decision. 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 Codevira MCP.

How many tools does the Codevira MCP server expose? +

48 tools across 3 categories: Execute, Read, Write. 28 are read-only. 20 can modify, create, or delete data.

How do I enforce a policy on Codevira MCP? +

Register the Codevira 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 Codevira MCP tool call.

Deterministic rules across all 48 Codevira MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CODEVIRA →

Free to start. No card required.

48 Codevira MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.