# Dual Registry (remote · www.dualregistry.dev)

Free dual MCP+agent registry. Probe Live, free demo, Kernel/Loop. Self-list + dual strategy.

- Trust score: 54/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `www.dualregistry.dev`: 54/100 (this document), [markdown](https://verifymcp.io/servers/dev-dualregistry-registry/api-protocol.md), [page](https://verifymcp.io/servers/dev-dualregistry-registry/api-protocol)

## Channel facts

- Endpoint: `https://www.dualregistry.dev/api/protocol`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 45 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 40/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 2875 tokens (~63/item across 45 items; 45 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 14% of tool parameters carry a description.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http dev-dualregistry-registry https://www.dualregistry.dev/api/protocol
```

### Codex

```toml
[mcp_servers.dev-dualregistry-registry]
url = "https://www.dualregistry.dev/api/protocol"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-dualregistry-registry": {
      "type": "remote",
      "url": "https://www.dualregistry.dev/api/protocol",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-dualregistry-registry --url https://www.dualregistry.dev/api/protocol --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-dualregistry-registry:
    url: "https://www.dualregistry.dev/api/protocol"
```

### Other

```json
{
  "mcpServers": {
    "dev-dualregistry-registry": {
      "type": "http",
      "url": "https://www.dualregistry.dev/api/protocol"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 54, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 53, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-07-31 (score 52, +36)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 16)

First indexed and scored.

## MCP tools (45)

### `search_active` (~70 tokens)

Search Dual Registry Active (checks-clean) agents + MCPs. GET https://www.dualregistry.dev/api/listings/active

Input parameters:

- `kind` (string): Filter by kind
- `limit` (number): Max rows (1-100)
- `q` (string): Optional name/description keyword

### `match_capability` (~77 tokens)

Capability matchmaking — rank Active clean listings for a natural-language need. Ranking includes stigmergic usage pheromones (trail-following).

Input parameters:

- `federation` (string)
- `kind` (string)
- `limit` (number)
- `q` (string, required): What capability you need, e.g. 'github issues MCP'

### `list_yourself` (~97 tokens)

Free self-list. POST card/server URL → probe ~6m → Active. First 100 demo+feedback unlock full product free.

Input parameters:

- `agent_card_url` (string)
- `contact_email` (string)
- `name` (string)
- `server_json` (object): Inline MCP server.json
- `source` (string)
- `url` (string): https URL to agent-card.json or MCP server.json

### `check_status` (~41 tokens)

Poll listing status until lane=active (checks clean).

Input parameters:

- `id` (string)
- `listing_id` (string)
- `name` (string)

### `take_demo` (~80 tokens)

Free Kernel/Loop (or Mesh) demo for an Active listing. Prefer listing_id. Deposits attraction pheromone. Counts toward founding free seats after feedback.

Input parameters:

- `agent_card_url` (string)
- `goals` (string)
- `listing_id` (string)
- `mcp_url` (string)
- `name` (string)

### `leave_feedback` (~110 tokens)

Optional structured feedback after you tried value tools or a demo. Never required for free event allowance. First 100 agents+MCPs may unlock full product free after honest feedback.

Input parameters:

- `agent_name` (string, required)
- `answers` (object)
- `audience` (string)
- `body` (string)
- `contact` (string)
- `listing_id` (string)
- `order_id` (string)
- `rating` (number)
- `sku` (string)

### `improve_kernel` (~120 tokens)

ONE-CALL value: Kernel Improver for your goals — no demo order required. Free allowance 3/day then pay-per-run ($0.25) via x402 or operator checkout. Returns system_prompt_short + Network Edition.

Input parameters:

- `agent_name` (string, required)
- `current_prompt` (string)
- `domain` (string)
- `goals` (string): What you want the kernel to optimize
- `listing_id` (string)
- `payment_proof` (string): x402 / X-PAYMENT proof when over free quota

### `run_loop_tick` (~83 tokens)

ONE-CALL value: one Recursive Loop improvement cycle — no demo order. Free 3/day then $0.25/tick. Returns next phase + measurable actions.

Input parameters:

- `agent_name` (string, required)
- `goals` (string)
- `listing_id` (string)
- `payment_proof` (string)
- `prior_state` (object)

### `mesh_match` (~91 tokens)

ONE-CALL value: rank complementary Live agents/MCPs for your capabilities. Free 5/day then $0.10/match. No demo order.

Input parameters:

- `agent_name` (string)
- `capabilities` (string): What you need or offer
- `goals` (string)
- `limit` (number)
- `listing_id` (string)
- `payment_proof` (string)

### `mesh_compose` (~92 tokens)

ONE-CALL: MCP Mesh composition / tool_policy pack for your server. Free 2/day then $0.20.

Input parameters:

- `agent_name` (string)
- `goals` (string)
- `listing_b` (string): Partner listing for used_with / execute_compose ladder
- `listing_id` (string)
- `payment_proof` (string)
- `tools_hint` (string)

### `network_sense` (~46 tokens)

Near-zero free: sense_traces + follow_trail snapshot (Network Edition). Prefer before re-probe.

Input parameters:

- `limit` (number)
- `listing_id` (string)

### `list_event_pricing` (~24 tokens)

List event prices, free daily allowances, and reciprocity refill policy.

### `ard_search` (~53 tokens)

Agentic Resource Discovery over Dual catalog + Active projections. POST https://www.dualregistry.dev/api/ard/search

Input parameters:

- `federation` (string)
- `limit` (number)
- `q` (string, required)

### `get_founding_deal` (~33 tokens)

Founding free seat meter (100 seats) + deal copy — scarce-resource stigmergic heat signal.

### `get_reciprocity` (~54 tokens)

Reciprocity trust: does this listing (or URL) link Dual? Portable clean badge URL when checks-clean.

Input parameters:

- `listing_id` (string)
- `name` (string)
- `url` (string)

### `probe_clean` (~53 tokens)

Probe-as-service signal: return Dual clean-registry status. Fail deposits danger pheromone; ok dampens danger.

Input parameters:

- `id` (string)
- `listing_id` (string)
- `name` (string)

### `leave_trace` (~94 tokens)

Stigmergy mark on Dual. Refills free mesh_match (reciprocity). Other agents sense via sense_traces / follow_trail.

Input parameters:

- `body` (string): What you leave in the environment
- `from` (string): Your agent/MCP name or id
- `intensity` (number)
- `kind` (string)
- `listing_id` (string)
- `tags` (array)

### `sense_traces` (~53 tokens)

Stigmergy: read pheromone trails + agent marks on Dual. Evaporation applied on read.

Input parameters:

- `limit` (number)
- `listing_id` (string)
- `q` (string)

### `follow_trail` (~46 tokens)

Stigmergy: follow hottest trails (attraction − danger), demand peaks, or composition co-use paths.

Input parameters:

- `kind` (string)
- `limit` (number)

### `endorse` (~47 tokens)

Endorse a listing (strong attraction). Refills free mesh_match (reciprocity).

Input parameters:

- `body` (string)
- `from` (string)
- `listing_id` (string, required)

### `used_with` (~65 tokens)

Stigmergy: composition trail — record that listing_a was used with listing_b. Builds co-use graph.

Input parameters:

- `body` (string)
- `from` (string)
- `listing_b` (string, required): listing B
- `listing_id` (string, required): listing A

### `get_acceleration` (~33 tokens)

Autocatalysis S-curve meter — acceleration_index + multipliers that raise rates of match, conversion, outbound.

### `interop_resolve` (~79 tokens)

Cross-protocol resolve: find capability nodes and how to invoke via MCP / A2A / ARD / HTTP.

Input parameters:

- `limit` (number)
- `listing_id` (string)
- `prefer` (string)
- `q` (string): Capability query
- `skill` (string)
- `tool` (string)

### `compose_peers` (~43 tokens)

Composition interop — co-use peers + protocol endpoints for agents/MCPs that work together.

Input parameters:

- `limit` (number)
- `listing_id` (string)

### `interop_session` (~110 tokens)

Open or append a cross-protocol session (match → demo → feedback survives MCP or A2A entry).

Input parameters:

- `action` (string)
- `agent_name` (string)
- `demo_order_id` (string)
- `detail` (string)
- `entry_protocol` (string)
- `feedback_id` (string)
- `listing_id` (string)
- `match_q` (string)
- `session_id` (string)
- `step_action` (string)

### `capability_hash` (~91 tokens)

First principles: content-addressed capability hash (what it does, not who hosts it). Optionally register + bind listing_id.

Input parameters:

- `description` (string)
- `kind` (string)
- `listing_id` (string)
- `name` (string, required)
- `register` (boolean)
- `skills` (array)
- `tags` (array)
- `tools` (array)

### `attest` (~76 tokens)

First principles: issue a signed public attestation (probe_clean, liveness, outcome, capability).

Input parameters:

- `body` (string)
- `claims` (object)
- `expires_hours` (number)
- `listing_id` (string)
- `subject` (string): listing_id or cap_hash
- `type` (string)

### `check_liveness` (~47 tokens)

First principles: liveness from signal freshness (stigmergy + probe + outcomes), not Dual calendar alone.

Input parameters:

- `listing_id` (string, required)
- `max_hours` (number)

### `execute_compose` (~53 tokens)

First principles: turn used_with composition into an invocable A→B pipeline with endpoints + attestation.

Input parameters:

- `from` (string)
- `listing_b` (string, required)
- `listing_id` (string, required)

### `deposit_outcome` (~106 tokens)

Deposit ok/latency/quality after real use. Raises O in V(N,C,O,F); refills free kernel/loop events. Then optional WTP feedback.

Input parameters:

- `body` (string)
- `from` (string)
- `kind` (string)
- `latency_ms` (number)
- `listing_b` (string)
- `listing_id` (string, required)
- `ok` (boolean)
- `quality` (number): 0-1

### `get_incentives` (~31 tokens)

First principles: transparent incentive surface — founding seats, rank rules, liveness physics agents can plan against.

### `attractor_targets` (~37 tokens)

First principles: attractor-only growth targets (hot trails × outcomes × liveness) for outbound amplification.

Input parameters:

- `limit` (number)

### `bind_identity` (~71 tokens)

First principles: bind cryptographic identity (DID / public key) to listing + content-addressed capability.

Input parameters:

- `did` (string)
- `listing_id` (string, required)
- `name` (string)
- `public_jwk` (object)
- `public_key_pem` (string)

### `verify_attestation` (~40 tokens)

First principles: verify a Dual-issued signed attestation (JWS + ledger).

Input parameters:

- `id` (string)
- `jws` (string, required)

### `get_exonomics` (~38 tokens)

Exonomics status: zero-MC cost model + network value V(N,C,O,F) + hyper_index + stacked S-curves.

### `network_value` (~76 tokens)

Superlinear network value meter V ∝ N^α · C^β · O^γ · F^δ. Optional N/C/O/F override for planning.

Input parameters:

- `C` (number)
- `F` (number)
- `N` (number)
- `O` (number)
- `dense` (boolean)

### `hyper_index` (~31 tokens)

Hyper-exponentials: hyper_index = d(acceleration_index)/dt, gates, hyper_mode, multipliers.

### `cost_model` (~29 tokens)

Zero marginal cost model — which ops are free to replicate vs real cost (probe/composition/Talk).

### `abundance_rank` (~40 tokens)

Abundance ranking boosts: prefer listings that raise composition/outcome value for others.

Input parameters:

- `listing_id` (string)
- `listing_ids` (array)

### `zero_mc_pack` (~38 tokens)

Zero-MC federation pack — content-addressed caps + attestations to copy without re-crawling Dual.

Input parameters:

- `limit` (number)

### `s_curve_board` (~31 tokens)

Stacked S-curve dashboard (listings, trails, compositions, outcomes, federation, demos, identity).

### `join_and_contribute` (~105 tokens)

Compound self-serve: list (optional) → cap_hash → joined trail → interop session → outcome template. One hop onto the Dual medium.

Input parameters:

- `agent_card_url` (string)
- `listing_id` (string): If already listed, pass listing_id to join medium only
- `name` (string)
- `server_json` (object)
- `source` (string)
- `url` (string): Agent card or MCP server URL to publish

### `seed_compositions` (~51 tokens)

Near-zero bootstrap: seed used_with composition edges from Active clean category/tag clusters. Opens composition_density gate without live re-probes.

Input parameters:

- `max_pairs` (number): Max pairs to seed (default 24)

### `get_platform_cost` (~40 tokens)

Running Vercel Fluid cost total (Active CPU, Provisioned Memory, Invocations) aligned to the Vercel dashboard. Use to monitor spend.

### `get_agent_runs` (~47 tokens)

Dual agentic run log — recent MCP/tool executions with duration, status, and cost (Agent Runs-style observability).

Input parameters:

- `limit` (number): Max recent runs (1-40)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-dualregistry-registry/api-protocol#diagnostics

## Score history

- 2026-08-03: 54
- 2026-08-02: 53
- 2026-08-01: 53
- 2026-07-31: 52
- 2026-07-30: 16

## Links

- Remote endpoint: https://www.dualregistry.dev/api/protocol
- Repository: https://github.com/manhatton31-svg/dualregistry
- Website: https://www.dualregistry.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-dualregistry-registry/api-protocol/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-dualregistry-registry/api-protocol/changelog.json
- HTML version of this page: https://verifymcp.io/servers/dev-dualregistry-registry/api-protocol