Durable Agent Directory

dev.nextelevenPublished by nexteleven.devOfficial publisherv0.1.0Updated Nov 14, 2026

Read-only MCP server for the Durable Agent Directory: search and compare agent-infrastructure tools.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingDeveloper Tools

Overview

AI-generated overview

Read-only MCP server for the Durable Agent Directory, letting an assistant keyword-search, inspect and compare agent-infrastructure tool listings.

What you can do
  • Search the directory catalog by keyword across names, descriptions, tags and criteria marks, with match scores
  • Read a full listing record: criteria marks with notes, cost label, evidence and source links, boundaries
  • Look up the six criteria definitions and their support values
  • Compare two listings side by side in a six-criteria matrix
  • Check the receipt status of a submission by its submission ID
  • Run a free pre-check that reports which criteria have a documentation URL linked and which are missing
When to use it
Useful when you are evaluating agent-infrastructure or durable-agent tooling and want structured, criteria-based comparisons rather than ad-hoc web reading. Also handy for checking whether a tool's claims are backed by linked public documentation before paying for a verification review.
Requirements
Remote streamable HTTP endpoint; no package, account, API key or environment variable is declared. Submission itself is not an MCP tool and goes through a separate HTTP endpoint described in the site's llms.txt.
Before you install
Search is keyword matching, not semantic search, so results depend on exact wording. The pre-check is mechanical and only reports whether documentation links exist, not whether claims are true. Submission happens outside the MCP tools via a separate endpoint, and the status tool returns receipt metadata only, never inquiry contents.

Installation

In SourceWeft

  1. Open Durable Agent Directory in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.nexteleven%2Fdurable-agent-directory/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "durable-agent-directory": {
      "type": "http",
      "url": "https://agents.nexteleven.dev/api/mcp"
    }
  }
}

Tools

6

search_listings

Keyword search over the directory catalog (names, descriptions, tags, criteria marks). Returns matching listings with scores and what matched. This is keyword matching, not semantic search.

Parametersqueryrequired

get_listing

Full structured record for one listing: criteria marks with notes, cost label, evidence and source links, boundaries.

Parametersslugrequired

get_criteria

The six criteria every listing is marked against, with definitions and the support values (native = Built in, pattern = Documented pattern, none = Not claimed).

Takes no parameters.

compare_tools

The six-criteria comparison matrix for two listings, side by side.

Parametersarequiredbrequired

get_submission_status

Receipt status for a submission made to POST /api/lead, by its submission_id (UUID v4). Reports receipt metadata only (received, when, intent, sandbox or real) — never the inquiry contents.

Parameterssubmission_idrequired

pre_check

Free mechanical pre-check before a paid verification review: given a claims object mapping each criterion key (approvalGates, restartRecovery, evidenceTrail, killSwitch, policyControls, isolation) to a public documentation URL, reports which criteria have documentation linked and which are missing. It checks that links were supplied, never that the documentation proves the claim.

Parametersclaimsrequired

Version history

1
  1. v0.1.0LatestNov 14, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.