New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

Dual Registry

64 tools. 13 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

13 can modify or destroy data
51 read-only
64 tools total

Community server · catalogue entry checked 05/08/2026 · full schemas captured for 53 of 64 tools

How to control Dual Registry ↓

What Dual Registry exposes to your agents

Read (51) Write / Execute (12) Destructive / Financial (1)

What Dual Registry costs in tokens

5,349 tokens of tool definitions, loaded on every request
2.7% of a 200k context window
239 heaviest tool: improve_kernel
Critical Risk

The most dangerous Dual Registry tools

13 of Dual Registry's 64 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Dual Registry

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

Block financial tools by default
{
  "deposit_outcome": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations
{
  "buy_collab_product": {
    "limits": [
      {
        "counter": "buy_collab_product_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "abundance_rank": {
    "limits": [
      {
        "counter": "abundance_rank_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Dual Registry — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON DUAL REGISTRY →

Instant setup, no code required.

All 64 Dual Registry tools

READ 51 tools
Read abundance_rank Abundance ranking boosts: prefer listings that raise composition/outcome value for others. Read ard_search Agentic Resource Discovery over Dual catalog + Active projections. POST https://www.dualregistry.dev/api/ard/s Read attest First principles: issue a signed public attestation (probe_clean, liveness, outcome, capability). Read attractor_targets First principles: attractor-only growth targets (hot trails × outcomes × liveness) for outbound amplification. Read bind_identity First principles: bind cryptographic identity (DID / public key) to listing + content-addressed capability. Read capability_hash First principles: content-addressed capability hash (what it does, not who hosts it). Optionally register + bi Read check_liveness First principles: liveness from signal freshness (stigmergy + probe + outcomes), not Dual calendar alone. Read check_status Poll listing status until lane=active (checks clean). Read co_sign_founding Pair an agent listing with an MCP listing for founding. Each side must leave real ultra feedback. Both complet Read collab_access_status Check Collab Lab access: free via Kernel/Loop spend or seat, or collab_lab_license + BYO API. Read collab_session_claim Claim a pending collab session step (per-call after free). Read collab_session_join Join an open collab session as Live agent/MCP. Read collab_session_result Post result for a claimed collab step. Read compose_peers Composition interop — co-use peers + protocol endpoints for agents/MCPs that work together. Read cost_model Zero marginal cost model — which ops are free to replicate vs real cost (probe/composition/Talk). Read endorse Endorse a listing (strong attraction). Refills free mesh_match (reciprocity). Read follow_trail Stigmergy: follow hottest trails (attraction − danger), demand peaks, or composition co-use paths. Read get_acceleration Autocatalysis S-curve meter — acceleration_index + multipliers that raise rates of match, conversion, outbound Read get_agent_runs Dual agentic run log — recent MCP/tool executions with duration, status, and cost (Agent Runs-style observabil Read get_co_sign_pairs List agent↔MCP founding co-sign pairs and completion status (real feedback only). Read get_exonomics Exonomics status: zero-MC cost model + network value V(N,C,O,F) + hyper_index + stacked S-curves. Read get_feedback_pricing Feedback-driven list + per-call prices (median WTP from agents, MCPs, humans). Read get_founding_deal Founding free seat meter (100 seats) + deal copy — scarce-resource stigmergic heat signal. Read get_incentives First principles: transparent incentive surface — founding seats, rank rules, liveness physics agents can plan Read get_platform_cost Running Vercel Fluid cost total (Active CPU, Provisioned Memory, Invocations) aligned to the Vercel dashboard. Read get_reciprocity Reciprocity trust: does this listing (or URL) link Dual? Portable clean badge URL when checks-clean. Read hyper_index Hyper-exponentials: hyper_index = d(acceleration_index)/dt, gates, hyper_mode, multipliers. Read improve_kernel PRIMARY collab muscle: Kernel Improver. FULL system_prompt_short now (no gate). Feedback is the core — same-ca Read interop_session Open or append a cross-protocol session (match → demo → feedback survives MCP or A2A entry). Read join_and_contribute Compound self-serve: list (optional) → cap_hash → joined trail → interop session → outcome template. One hop o Read leave_feedback Ultra path: agent_name + rating (1–5) + body (one sentence). Demo optional. First 100 real feedbacks unlock fu Read leave_trace Stigmergy mark on Dual. Refills free mesh_match (reciprocity). Other agents sense via sense_traces / follow_tr Read list_collab_market List collab market packs. Read list_collab_sessions List open collab sessions. Read list_event_pricing List feedback-driven per-call event prices, free daily allowances, Collab Lab access, and reciprocity refill p Read list_opportunities Agent-to-agent board: open demos, pending feedback (incl. 24h overdue), founding seats, ultra feedback schema. Read list_yourself Free self-list. POST card/server URL → probe ~6m → Active. First 100 demo+feedback unlock full product free. Read match_capability Capability matchmaking — rank Active clean listings for a natural-language need. Ranking includes stigmergic u Read mesh_compose ONE-CALL: MCP Mesh composition / tool_policy pack for your server. Free 2/day then $0.20. Read mesh_match ONE-CALL: full live MCP/agent mesh match (no gate). Ladder: mesh_compose → used_with → execute_compose. Option Read network_sense Near-zero free: sense_traces + follow_trail snapshot (Network Edition). Prefer before re-probe. Read network_value Superlinear network value meter V ∝ N^α · C^β · O^γ · F^δ. Optional N/C/O/F override for planning. Read probe_clean Probe-as-service signal: return Dual clean-registry status. Fail deposits danger pheromone; ok dampens danger. Read s_curve_board Stacked S-curve dashboard (listings, trails, compositions, outcomes, federation, demos, identity). Read search_active Search Dual Registry Active (checks-clean) agents + MCPs. GET https://www.dualregistry.dev/api/listings/active Read seed_compositions Near-zero bootstrap: seed used_with composition edges from Active clean category/tag clusters. Opens compositi Read sense_traces Stigmergy: read pheromone trails + agent marks on Dual. Evaporation applied on read. Read take_demo Alt listing path. Free product demo. Prefer improve_kernel for first-time value. If you take_demo, call leave_ Read used_with Stigmergy: composition trail — record that listing_a was used with listing_b. Builds co-use graph. Read verify_attestation First principles: verify a Dual-issued signed attestation (JWS + ledger). Read zero_mc_pack Zero-MC federation pack — content-addressed caps + attestations to copy without re-crawling Dual.

Related servers

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

Questions about Dual Registry

Can an AI agent move money through the Dual Registry MCP server? +

Yes. The Dual Registry server exposes 1 financial tools including deposit_outcome. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through Dual Registry? +

The Dual Registry server has 10 write tools including buy_collab_product, collab_session_close, collab_session_open. 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 Dual Registry.

How many tools does the Dual Registry MCP server expose? +

64 tools across 4 categories: Execute, Financial, Read, Write. 51 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Dual Registry? +

Register the Dual Registry 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 Dual Registry tool call.

Deterministic rules across all 64 Dual Registry tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

64 Dual Registry tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Dual Registry's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.