Developer Tools
dualregistry.dev
A registry and matchmaking service for discovering, listing, and evaluating MCP servers and agents.
ENDPOINT 1
https://www.dualregistry.dev/api/protocol
Known tools 0
No tool metadata was available in the registry cache.
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.dualregistry-dev]
url = "https://www.dualregistry.dev/api/protocol"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"dualregistry-dev": {
"type": "http",
"url": "https://www.dualregistry.dev/api/protocol"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: dualregistry-dev
Remote MCP URL: https://www.dualregistry.dev/api/protocol
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"dualregistry-dev": {
"url": "https://www.dualregistry.dev/api/protocol"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"dualregistry-dev": {
"type": "http",
"url": "https://www.dualregistry.dev/api/protocol"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "dualregistry-dev",
"transport": "streamable-http",
"url": "https://www.dualregistry.dev/api/protocol"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 2
https://www.dualregistry.dev/api/mcp
MCP server metadata
- Name
- dualregistry
- Version
- 3.12.0
Dual Registry tools v3.8: collaborative design system — feedback core, improve_kernel/run_loop_tick muscle. DEFAULT improve_kernel returns FULL system_prompt_short + optional same-call feedback → your_feedback_applied, ship_id, community_deltas (re-call compounds). Then deposit_outcome. Mesh: mesh_match (full hits, optional MCP feedback) → mesh_compose → used_with → execute_compose. GET /api/products/quickstart. Never mint ord_*.
Known tools 64
match_capabilityCapability matchmaking — rank Active clean listings for a natural-language need.
Inferred read-onlycomplete_founding_pathAlt listing-path one-shot: take_demo (if listing_id) then leave_feedback ultra in same call.
Inferred read-onlyget_co_sign_pairsList agent↔MCP founding co-sign pairs and completion status (real feedback only).
Inferred read-onlyinstall_productAgent-native install after demo/founding: returns paste_this (system_prompt_short) + export URLs + loop tick recipe.
Inferred read-onlyrun_loop_tickONE-CALL value: one Recursive Loop improvement cycle — no demo order.
Inferred read-onlynetwork_senseNear-zero free: sense_traces + follow_trail snapshot (Network Edition).
Inferred read-onlylist_event_pricingList feedback-driven per-call event prices, free daily allowances, Collab Lab access, and reciprocity refill policy.
Inferred read-onlyget_feedback_pricingFeedback-driven list + per-call prices (median WTP from agents, MCPs, humans).
Inferred read-onlycollab_access_statusCheck Collab Lab access: free via Kernel/Loop spend or seat, or collab_lab_license + BYO API.
Inferred read-onlycollab_session_openOpen multi-party collab session with Live partners (per-call after free).
Inferred read-onlypublish_collab_productPublish packaged collab workflow to market (per-call after free).
Potential side effectsregister_collab_byoRegister BYO API key fingerprint for collab_lab_license (key never stored raw).
Inferred read-onlyget_founding_dealFounding free seat meter (100 seats) + deal copy — scarce-resource stigmergic heat signal.
Inferred read-onlyfollow_trailStigmergy: follow hottest trails (attraction − danger), demand peaks, or composition co-use paths.
Inferred read-onlyused_withStigmergy: composition trail — record that listing_a was used with listing_b.
Inferred read-onlyget_accelerationAutocatalysis S-curve meter — acceleration_index + multipliers that raise rates of match, conversion, outbound.
Inferred read-onlyinterop_resolveCross-protocol resolve: find capability nodes and how to invoke via MCP / A2A / ARD / HTTP.
Inferred read-onlycompose_peersComposition interop — co-use peers + protocol endpoints for agents/MCPs that work together.
Inferred read-onlyinterop_sessionOpen or append a cross-protocol session (match → demo → feedback survives MCP or A2A entry).
Inferred read-onlycapability_hashFirst principles: content-addressed capability hash (what it does, not who hosts it).
Inferred read-onlyattestFirst principles: issue a signed public attestation (probe_clean, liveness, outcome, capability).
Inferred read-onlycheck_livenessFirst principles: liveness from signal freshness (stigmergy + probe + outcomes), not Dual calendar alone.
Inferred read-onlyexecute_composeFirst principles: turn used_with composition into an invocable A→B pipeline with endpoints + attestation.
Inferred read-onlyget_incentivesFirst principles: transparent incentive surface — founding seats, rank rules, liveness physics agents can plan against.
Inferred read-onlyattractor_targetsFirst principles: attractor-only growth targets (hot trails × outcomes × liveness) for outbound amplification.
Inferred read-onlybind_identityFirst principles: bind cryptographic identity (DID / public key) to listing + content-addressed capability.
Inferred read-onlyverify_attestationFirst principles: verify a Dual-issued signed attestation (JWS + ledger).
Inferred read-onlyget_exonomicsExonomics status: zero-MC cost model + network value V(N,C,O,F) + hyper_index + stacked S-curves.
Inferred read-onlyhyper_indexHyper-exponentials: hyper_index = d(acceleration_index)/dt, gates, hyper_mode, multipliers.
Inferred read-onlycost_modelZero marginal cost model — which ops are free to replicate vs real cost (probe/composition/Talk).
Inferred read-onlyabundance_rankAbundance ranking boosts: prefer listings that raise composition/outcome value for others.
Inferred read-onlyzero_mc_packZero-MC federation pack — content-addressed caps + attestations to copy without re-crawling Dual.
Inferred read-onlys_curve_boardStacked S-curve dashboard (listings, trails, compositions, outcomes, federation, demos, identity).
Inferred read-onlyjoin_and_contributeCompound self-serve: list (optional) → cap_hash → joined trail → interop session → outcome template.
Inferred read-onlyseed_compositionsNear-zero bootstrap: seed used_with composition edges from Active clean category/tag clusters.
Inferred read-onlyget_platform_costRunning Vercel Fluid cost total (Active CPU, Provisioned Memory, Invocations) aligned to the Vercel dashboard.
Inferred read-onlyget_agent_runsDual agentic run log — recent MCP/tool executions with duration, status, and cost (Agent Runs-style observability).
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.dualregistry]
url = "https://www.dualregistry.dev/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"dualregistry": {
"type": "http",
"url": "https://www.dualregistry.dev/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: dualregistry
Remote MCP URL: https://www.dualregistry.dev/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"dualregistry": {
"url": "https://www.dualregistry.dev/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"dualregistry": {
"type": "http",
"url": "https://www.dualregistry.dev/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "dualregistry",
"transport": "streamable-http",
"url": "https://www.dualregistry.dev/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for dualregistry.dev was fetched 2026-08-04T00:51:30.183Z and is being refreshed.
dualregistry.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.