// SCAN REPORT

Myco — Agent-First Cognitive Substrate

21 tools. 5 can modify or destroy data without limits.

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

Last updated: 27 Jun 2026

5 can modify or destroy data

16 read-only

21 tools total

Community server · catalogue entry verified 27/06/2026

How to control Myco — Agent-First Cognitive Substrate ↓

TOOL MAP

What Myco — Agent-First Cognitive Substrate exposes to your agents

Read (16) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Myco — Agent-First Cognitive Substrate tools

Execute · High myco_advance_cycle This tool executes a computational cycle with side effects on the graph substrate state. Execute · High myco_run_immune_check This tool executes a triggered operation ('Trigger an ad-hoc immune verification scan') that initiates internal integrity verification processes and produces observable side effects (emitting immune sporocarp events visi Write · Medium myco_register_axis This tool creates or modifies substrate configuration by registering a new axis—a reversible write operation. Write · Medium myco_submit_mutation This tool modifies the substrate's internal state by writing new DAG nodes based on submitted mutations.

5 of Myco — Agent-First Cognitive Substrate's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Myco — Agent-First Cognitive Substrate

PolicyLayer is an MCP gateway — it sits between your AI agents and Myco — Agent-First Cognitive Substrate, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "myco_perturb_axis": {
    "limits": [
      {
        "counter": "myco_perturb_axis_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "myco_current_intent": {
    "limits": [
      {
        "counter": "myco_current_intent_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 Myco — Agent-First Cognitive Substrate — 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 MYCO — AGENT-FIRST COGNITIVE SUBSTRATE →

Instant setup, no code required.

FULL CATALOGUE

All 21 Myco — Agent-First Cognitive Substrate tools

EXECUTE 2 tools

Execute myco_advance_cycle Run one substrate metabolic cycle. Triggers gradient advance, fruiting checks, and sporocarp emission. Returns Execute myco_run_immune_check Trigger an ad-hoc immune verification scan. The substrate runs comprehensive integrity checks (substrate_id we

WRITE 3 tools

Write myco_perturb_axis Apply a delta (positive or negative) to a registered axis. This is the operator-side input channel into the su Write myco_register_axis Register a new gradient axis on the substrate. Axes are operator-defined channels through which deltas accumul Write myco_submit_mutation Submit a mutation for the substrate to classify. The substrate classifies via L1/GOVERNANCE rules: daily mutat

READ 16 tools

Read myco_current_intent Compute the substrate Read myco_enumerate_dag_since Enumerate DAG node hashes added since a given prev_tip (or from genesis if omitted), with full per-node metada Read myco_orient Orient yourself at the START of a session — the first thing a new pilot should do. In one call this surfaces ( Read myco_query_forged_understanding Query the substrate Read myco_query_immune_events List recent immune events recorded by the substrate Read myco_query_migration_pending P03 §10.4 (Resumable Evolution): Report whether a two-phase schema migration is currently in flight. When an o Read myco_query_raw_material Query the substrate Read myco_query_recent_nodes List the last N DAG nodes (sporocarps) in the substrate Read myco_query_self_euthanasia_proposals P7 必朽 (Endogenous-pair Mortality): List the substrate Read myco_query_substrate_id PERCEPTION (P8 §5.6): report this substrate Read myco_query_substrate_observatory PERCEPTION (Phase α / M24.5 observatory snapshot): expose ALL cultivar vital signs from inside the substrate s Read myco_read_node_content Read back the HUMAN-READABLE content of a single DAG node by its hash — fetched directly via the substrate (AN Read myco_recall Read your compact \ Read myco_shutdown_substrate Gracefully shut down the substrate. After this call, no more substrate operations will work in this session. Read myco_snapshot Read current values of all registered gradient axes. Useful for inspection between cycles. Read substrate_info Report substrate version + Python kernel/tropism version + Python interpreter version. Useful for verifying wh

EXPLORE

Related servers

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

FAQ

Questions about Myco — Agent-First Cognitive Substrate

How do I prevent bulk modifications through Myco — Agent-First Cognitive Substrate? +

The Myco — Agent-First Cognitive Substrate server has 3 write tools including myco_perturb_axis, myco_register_axis, myco_submit_mutation. 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 Myco — Agent-First Cognitive Substrate.

How many tools does the Myco — Agent-First Cognitive Substrate MCP server expose? +

21 tools across 3 categories: Execute, Read, Write. 16 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Myco — Agent-First Cognitive Substrate? +

Register the Myco — Agent-First Cognitive Substrate 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 Myco — Agent-First Cognitive Substrate tool call.

Deterministic rules across all 21 Myco — Agent-First Cognitive Substrate tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MYCO — AGENT-FIRST COGNITIVE SUBSTRATE →

Instant setup, no code required.

21 Myco — Agent-First Cognitive Substrate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.