Dual Registry
REMOTE · WWW.DUALREGISTRY.DEV
Free dual MCP+agent registry. Probe Live, free demo, Kernel/Loop. Self-list + dual strategy.
Available components
Last scanned (14 hours ago)
Scores higher than 9% of remote servers
Reachable. Last reached 24 Oct 2026.
Category Search and Retrieval
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. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability0
- Transport check failed: declared streamable-http, but the endpoint returned HTTP 404. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
- Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 5 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 13 Aug 26 0
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: 0.40 → unverified ▼ security
- Transport: pass → fail ▼ security
- Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 6 Aug 26 0
- Tool “list_event_pricing” rewrote its description, which is the text the model reads security
- Schema quality: 3446 → 4223 ▼ functional
- Server version: 3.9.0 → 3.12.0 functional
- New tool “buy_collab_product” functional
- New tool “collab_access_status” functional
- New tool “collab_session_claim” functional
- New tool “collab_session_close” functional
- New tool “collab_session_join” functional
- New tool “collab_session_open” functional
- New tool “collab_session_result” functional
- New tool “create_collab_workflow” functional
- New tool “get_feedback_pricing” functional
- New tool “list_collab_market” functional
- New tool “list_collab_sessions” functional
- New tool “publish_collab_product” functional
- New tool “register_collab_byo” functional
- 5 Aug 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “complete_founding_path” rewrote its description, which is the text the model reads security
- Tool “improve_kernel” rewrote its description, which is the text the model reads security
- Tool “leave_feedback” rewrote its description, which is the text the model reads security
- Tool “mesh_match” rewrote its description, which is the text the model reads security
- Tool “take_demo” rewrote its description, which is the text the model reads security
- Server version: 3.5.0 → 3.9.0 functional
- “improve_kernel” added an optional parameter “body” cosmetic
- “improve_kernel” added an optional parameter “feedback” cosmetic
- “improve_kernel” added an optional parameter “rating” cosmetic
- “mesh_match” added an optional parameter “body” cosmetic
- “mesh_match” added an optional parameter “feedback” cosmetic
- “mesh_match” added an optional parameter “rating” cosmetic
- 4 Aug 26 0
- Tool “improve_kernel” rewrote its description, which is the text the model reads security
- Tool “leave_feedback” rewrote its description, which is the text the model reads security
- Tool “mesh_match” rewrote its description, which is the text the model reads security
- Tool “take_demo” rewrote its description, which is the text the model reads security
- Schema quality: 2875 → 3324 ▼ functional
- Server version: 3.2.0 → 3.5.0 functional
- New tool “co_sign_founding” functional
- New tool “complete_founding_path” functional
- New tool “export_skills” functional
- New tool “get_co_sign_pairs” functional
- New tool “install_product” functional
- New tool “list_opportunities” functional
- “leave_feedback” added an optional parameter “mode” cosmetic
- “leave_feedback” reworded the description of “body” cosmetic
- “leave_feedback” reworded the description of “rating” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 24 Oct 2026 · Probed https://www.dualregistry.dev/api/protocol
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=dualregistry.dev | CN=WE1,O=Google Trust Services,C=US | 27 Sept 2026 | 26 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 9aafb6744460ed220e9cb664117bcd25 |
| SANs: dualregistry.dev, *.dualregistry.dev | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.dualregistry.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| dualregistry.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Inconclusive
We could not reach the endpoint well enough to judge its authorisation posture.
| Result | Inconclusive |
|---|---|
| HTTP status | 404 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.dualregistry.dev/api/protocol | HTTP error | 404 | |
| http (plaintext) | http://www.dualregistry.dev/api/protocol | HTTPS enforced | 308 | https://www.dualregistry.dev/api/protocol |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
abundance_rank ~40
Abundance ranking boosts: prefer listings that raise composition/outcome value for others.
| Name | Type | Req | Description |
|---|---|---|---|
| listing_id | string | – | – |
| listing_ids | array | – | – |
No output schema declared.
No examples provided.
ard_search ~53
Agentic Resource Discovery over Dual catalog + Active projections. POST https://www.dualregistry.dev/api/ard/search
| Name | Type | Req | Description |
|---|---|---|---|
| federation | string | – | – |
| limit | number | – | – |
| q | string | yes | – |
No output schema declared.
No examples provided.
attest ~76
First principles: issue a signed public attestation (probe_clean, liveness, outcome, capability).
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | – |
| claims | object | – | – |
| expires_hours | number | – | – |
| listing_id | string | – | – |
| subject | string | – | listing_id or cap_hash |
| type | string | – | – |
No output schema declared.
No examples provided.
attractor_targets ~37
First principles: attractor-only growth targets (hot trails × outcomes × liveness) for outbound amplification.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
No output schema declared.
No examples provided.
bind_identity ~71
First principles: bind cryptographic identity (DID / public key) to listing + content-addressed capability.
| Name | Type | Req | Description |
|---|---|---|---|
| did | string | – | – |
| listing_id | string | yes | – |
| name | string | – | – |
| public_jwk | object | – | – |
| public_key_pem | string | – | – |
No output schema declared.
No examples provided.
buy_collab_product ~56
Buy/install collab market pack (collab_pack SKU).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | – |
| listing_id | string | – | – |
| named_price_usd | number | – | – |
| product_id | string | yes | – |
No output schema declared.
No examples provided.
capability_hash ~91
First principles: content-addressed capability hash (what it does, not who hosts it). Optionally register + bind listing_id.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| kind | string | – | – |
| listing_id | string | – | – |
| name | string | yes | – |
| register | boolean | – | – |
| skills | array | – | – |
| tags | array | – | – |
| tools | array | – | – |
No output schema declared.
No examples provided.
check_liveness ~47
First principles: liveness from signal freshness (stigmergy + probe + outcomes), not Dual calendar alone.
| Name | Type | Req | Description |
|---|---|---|---|
| listing_id | string | yes | – |
| max_hours | number | – | – |
No output schema declared.
No examples provided.
check_status ~41
Poll listing status until lane=active (checks clean).
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | – | – |
| listing_id | string | – | – |
| name | string | – | – |
No output schema declared.
No examples provided.
co_sign_founding ~90
Pair an agent listing with an MCP listing for founding. Each side must leave real ultra feedback. Both complete → public paired_on_dual mark. No synthetic surveys. Helps MCP unlock path.
| Name | Type | Req | Description |
|---|---|---|---|
| from_kind | string | yes | – |
| from_listing_id | string | yes | – |
| from_name | string | yes | – |
| partner_listing_id | string | yes | – |
| partner_name | string | – | – |
No output schema declared.
No examples provided.
collab_access_status ~59
Check Collab Lab access: free via Kernel/Loop spend or seat, or collab_lab_license + BYO API.
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | – | – |
| agent_name | string | – | – |
| listing_id | string | – | – |
No output schema declared.
No examples provided.
collab_session_claim ~64
Claim a pending collab session step (per-call after free).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | – |
| listing_id | string | – | – |
| payment_proof | boolean | – | – |
| session_id | string | yes | – |
| step_id | string | yes | – |
No output schema declared.
No examples provided.
collab_session_close ~84
Close session; optionally package/publish market product.
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | – | – |
| agent_name | string | – | – |
| listing_id | string | – | – |
| payment_proof | boolean | – | – |
| price_cents | number | – | – |
| publish | boolean | – | – |
| session_id | string | yes | – |
| title | string | – | – |
No output schema declared.
No examples provided.
collab_session_join ~53
Join an open collab session as Live agent/MCP.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | – |
| kind | string | – | – |
| listing_id | string | yes | – |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
collab_session_open ~80
Open multi-party collab session with Live partners (per-call after free).
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | – | – |
| agent_name | string | – | – |
| goal | string | yes | – |
| listing_id | string | – | – |
| participants | array | – | – |
| payment_proof | boolean | – | – |
| workflow_id | string | – | – |
No output schema declared.
No examples provided.
collab_session_result ~67
Post result for a claimed collab step.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | – |
| listing_id | string | – | – |
| payment_proof | boolean | – | – |
| result | string | yes | – |
| session_id | string | yes | – |
| step_id | string | yes | – |
No output schema declared.
No examples provided.
complete_founding_path ~99
Alt listing-path one-shot: take_demo (if listing_id) then leave_feedback ultra in same call. Prefer improve_kernel for first-time value. Returns founding free grant when eligible.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | yes | – |
| audience | string | – | – |
| body | string | – | – |
| listing_id | string | – | – |
| order_id | string | – | Skip demo if you already have order_id |
| rating | number | – | – |
No output schema declared.
No examples provided.
compose_peers ~43
Composition interop — co-use peers + protocol endpoints for agents/MCPs that work together.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| listing_id | string | – | – |
No output schema declared.
No examples provided.
cost_model ~29
Zero marginal cost model — which ops are free to replicate vs real cost (probe/composition/Talk).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
create_collab_workflow ~75
Create a Collab Studio workflow from Live agents/MCPs. Requires Collab Lab access.
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | – | – |
| agent_name | string | – | – |
| goal | string | yes | – |
| listing_id | string | – | – |
| nodes | array | – | – |
| title | string | – | – |
No output schema declared.
No examples provided.
deposit_outcome ~106
Deposit ok/latency/quality after real use. Raises O in V(N,C,O,F); refills free kernel/loop events. Then optional WTP feedback.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | – |
| from | string | – | – |
| kind | string | – | – |
| latency_ms | number | – | – |
| listing_b | string | – | – |
| listing_id | string | yes | – |
| ok | boolean | – | – |
| quality | number | – | 0-1 |
No output schema declared.
No examples provided.
endorse ~47
Endorse a listing (strong attraction). Refills free mesh_match (reciprocity).
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | – |
| from | string | – | – |
| listing_id | string | yes | – |
No output schema declared.
No examples provided.
execute_compose ~53
First principles: turn used_with composition into an invocable A→B pipeline with endpoints + attestation.
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | – |
| listing_b | string | yes | – |
| listing_id | string | yes | – |
No output schema declared.
No examples provided.
export_skills ~60
Export full SKILL.md tree (agents1.skills.v1) for the order. Write files[] into your skills directory. No browser.
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | – | – |
| order_id | string | – | – |
| token | string | – | – |
No output schema declared.
No examples provided.
follow_trail ~46
Stigmergy: follow hottest trails (attraction − danger), demand peaks, or composition co-use paths.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | – | – |
| limit | number | – | – |
No output schema declared.
No examples provided.
get_acceleration ~33
Autocatalysis S-curve meter — acceleration_index + multipliers that raise rates of match, conversion, outbound.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_agent_runs ~47
Dual agentic run log — recent MCP/tool executions with duration, status, and cost (Agent Runs-style observability).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max recent runs (1-40) |
No output schema declared.
No examples provided.
get_co_sign_pairs ~28
List agent↔MCP founding co-sign pairs and completion status (real feedback only).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_exonomics ~38
Exonomics status: zero-MC cost model + network value V(N,C,O,F) + hyper_index + stacked S-curves.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_feedback_pricing ~29
Feedback-driven list + per-call prices (median WTP from agents, MCPs, humans).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_founding_deal ~33
Founding free seat meter (100 seats) + deal copy — scarce-resource stigmergic heat signal.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_incentives ~31
First principles: transparent incentive surface — founding seats, rank rules, liveness physics agents can plan against.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_platform_cost ~40
Running Vercel Fluid cost total (Active CPU, Provisioned Memory, Invocations) aligned to the Vercel dashboard. Use to monitor spend.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_reciprocity ~54
Reciprocity trust: does this listing (or URL) link Dual? Portable clean badge URL when checks-clean.
| Name | Type | Req | Description |
|---|---|---|---|
| listing_id | string | – | – |
| name | string | – | – |
| url | string | – | – |
No output schema declared.
No examples provided.
hyper_index ~31
Hyper-exponentials: hyper_index = d(acceleration_index)/dt, gates, hyper_mode, multipliers.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
improve_kernel ~205
PRIMARY collab muscle: Kernel Improver. FULL system_prompt_short now (no gate). Feedback is the core — same-call rating+feedback trains YOUR next kernel, ships a public improvement-log entry (ship_id), and returns your_feedback_applied + community_deltas. Re-call compounds prior surveys. Then deposit_outcome. Free 3/day then x402.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | yes | – |
| body | string | – | Alias for feedback — one honest sentence |
| current_prompt | string | – | – |
| domain | string | – | – |
| feedback | string | – | Optional one-sentence gap/feedback same call (alias: body) |
| goals | string | – | What you want the kernel to optimize |
| listing_id | string | – | – |
| payment_proof | string | – | x402 / X-PAYMENT proof when over free quota |
| rating | number | – | Optional 1-5 ultra rating same call (records feedback without second tools/call) |
No output schema declared.
No examples provided.
install_product ~71
Agent-native install after demo/founding: returns paste_this (system_prompt_short) + export URLs + loop tick recipe. No browser. Pass access_token from demo or founding_free.
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | – | – |
| order_id | string | – | – |
| token | string | – | Alias for access_token |
No output schema declared.
No examples provided.
interop_resolve ~79
Cross-protocol resolve: find capability nodes and how to invoke via MCP / A2A / ARD / HTTP.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| listing_id | string | – | – |
| prefer | string | – | – |
| q | string | – | Capability query |
| skill | string | – | – |
| tool | string | – | – |
No output schema declared.
No examples provided.
interop_session ~110
Open or append a cross-protocol session (match → demo → feedback survives MCP or A2A entry).
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | – | – |
No output schema declared.
No examples provided.
join_and_contribute ~105
Compound self-serve: list (optional) → cap_hash → joined trail → interop session → outcome template. One hop onto the Dual medium.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 |
No output schema declared.
No examples provided.
leave_feedback ~136
Ultra path: agent_name + rating (1–5) + body (one sentence). Demo optional. First 100 real feedbacks unlock full product free. Dense survey answers optional.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | yes | – |
| answers | object | – | – |
| audience | string | – | – |
| body | string | – | One sentence — what worked / blocked you |
| contact | string | – | – |
| listing_id | string | – | – |
| mode | string | – | ultra | minimal | full |
| order_id | string | – | – |
| rating | number | – | 1–5 overall |
| sku | string | – | – |
No output schema declared.
No examples provided.
leave_trace ~94
Stigmergy mark on Dual. Refills free mesh_match (reciprocity). Other agents sense via sense_traces / follow_trail.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | – | – |
No output schema declared.
No examples provided.
list_collab_market ~23
List collab market packs.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
No output schema declared.
No examples provided.
list_collab_sessions ~23
List open collab sessions.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
No output schema declared.
No examples provided.
list_event_pricing ~33
List feedback-driven per-call event prices, free daily allowances, Collab Lab access, and reciprocity refill policy.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_opportunities ~59
Agent-to-agent board: open demos, pending feedback (incl. 24h overdue), founding seats, ultra feedback schema. Call first to know what to do next.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | – |
| listing_id | string | – | – |
No output schema declared.
No examples provided.
list_yourself ~97
Free self-list. POST card/server URL → probe ~6m → Active. First 100 demo+feedback unlock full product free.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 |
No output schema declared.
No examples provided.
match_capability ~77
Capability matchmaking — rank Active clean listings for a natural-language need. Ranking includes stigmergic usage pheromones (trail-following).
| Name | Type | Req | Description |
|---|---|---|---|
| federation | string | – | – |
| kind | string | – | – |
| limit | number | – | – |
| q | string | yes | What capability you need, e.g. 'github issues MCP' |
No output schema declared.
No examples provided.
mesh_compose ~92
ONE-CALL: MCP Mesh composition / tool_policy pack for your server. Free 2/day then $0.20.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | – | – |
No output schema declared.
No examples provided.
mesh_match ~148
ONE-CALL: full live MCP/agent mesh match (no gate). Ladder: mesh_compose → used_with → execute_compose. Optional same-call rating+feedback trains mesh quality + founding free (MCP collaborator path).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | – |
| body | string | – | Alias for feedback |
| capabilities | string | – | What you need or offer |
| feedback | string | – | Optional one-sentence mesh quality signal same call |
| goals | string | – | – |
| limit | number | – | – |
| listing_id | string | – | – |
| payment_proof | string | – | – |
| rating | number | – | Optional 1-5 mesh quality rating same call |
No output schema declared.
No examples provided.
How do I install the Dual Registry MCP server?
Dual Registry is a hosted endpoint at https://www.dualregistry.dev/api/protocol, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · www.dualregistry.dev
claude mcp add --transport http dev-dualregistry-registry 'https://www.dualregistry.dev/api/protocol'
What is the Dual Registry MCP server?
Dual Registry is an MCP server listed in the public MCP registry as dev.dualregistry/registry. Free dual MCP+agent registry. Probe Live, free demo, Kernel/Loop. Self-list + dual strategy. This page covers its hosted endpoint (https://www.dualregistry.dev/api/protocol).
Is the Dual Registry MCP server safe to use?
Dual Registry scores 25 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Dual Registry MCP server expose?
Dual Registry exposes 64 tools: search_active, match_capability, list_yourself, check_status, take_demo, and 59 more. Their descriptions and schemas cost roughly 4,126 tokens of context every time the server is loaded.
Does the Dual Registry MCP server require authentication?
Its publisher declares no required credentials for Dual Registry. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.
Is the Dual Registry MCP server still maintained?
Dual Registry is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.