Skip to content
Nonprofit Leader Guide logo

Nonprofit Leader Guide MCP server

Which servers in the official MCP registry are Nonprofit Leader Guide's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-21

← Back to Nonprofit Leader Guide

Whose server it is
  • Registry nameguide.nonprofitleader/guide-registryverified in the MCP registry

The registry name sits under nonprofitleader.guide. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools10
  • Server calls itselfbicycle-guide-registry
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 142 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-21
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer421 ms
  • Space in an agent's context≈ 2,367 tokensthe definitions of all its tools (10), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results10 of 10 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers10 tools · read 2026-10-21
  • list_guides

    List the bicycle.guide registry — every guide's home, status, access, standard, syndication and grounding, plus the distribution roll-up (including guides homed to a property with no rendering surface).

  • get_guide

    Get one guide's registry row by slug, with its artifact + routing-surface status.

  • list_taxonomy

    Get the bicycle.guide vocabulary — domains, shelves (with live guide counts), series, personas, guide_types, and the classification conventions (pillar/spoke, discriminant home, bicycle-guide-serves-all) as machine-readable data rather…

  • list_capabilities

    Traverse the capability spine joining books, guides (capability packages), KSAO-grade elements and jobs. Use min_guides=2 for the cross-cutting capabilities that span many guides, role=<role> for what a job requires…

  • search_guides

    Search published guides by topic. Returns matches, or a structured refusal with the nearest owned guides and the missing topic. No model call. Filter by persona or category.

  • list_disagreements

    Where does the field disagree? Returns cross-book tension names and the books on each pole (title, author, library_id) plus the guide URL. Filter by slug, persona, or category. Names and provenance only — no passages.

  • list_conditions

    List organizational conditions (identity, label, guide count, causal-role counts). Filter by draft domain, subdomain, or causal_role (driver|mediator|outcome). Names and counts only — no addresses, no passages.

  • get_answer

    Get one Answer — question, grounded answer, visible citations — by id or slug, in the Answer contract v0 shape (ANSWERS-PROGRAM.md). Read-only. Returns null if not found.

  • list_answers

    List Answers (contract v0), paginated with an opaque cursor. Read-only.

  • search_answers

    Search Answers by free-text query over question/answer text. Returns contract v0 records. Read-only.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "guide-registry": {
      "type": "http",
      "url": "https://nonprofitleader.guide/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http nonprofitleader https://nonprofitleader.guide/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://nonprofitleader.guide/mcp as a custom connector in the settings.

OpenAPI spec

8 paths, read 2026-10-21. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.