design-mcp-server

name	design-mcp-server
description	Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
metadata	{"author":"cyanheads","version":"2.20","audience":"external","type":"workflow"}

When to Use

• User says "I want to build a ___ MCP server"
• User has an API, database, or system they want to expose to LLMs
• User wants to plan tools before scaffolding
• Existing server needs a new capability area (design the addition, not just a single tool)

Do NOT use for single-tool additions — use add-tool directly.

Inputs

Gather before designing. Ask the user if not obvious from context:

1. Domain — what system, API, or capability is this server wrapping? Or is the server providing internal capability with no external dependency (computation, text/code utilities, in-memory state)?
2. Data sources / source of truth — APIs, databases, file systems, external services? Or is the server itself the source (in-memory state, pure computation, local-only utility, embedded model)?
3. Target users — what will the LLM (and its human) be trying to accomplish?
4. Scope constraints — read-only? write access? admin operations? what's off-limits?

If the domain has a public API, read its docs before designing. For internal-only servers, skip API research and go straight to user goals. Don't design from vibes either way.

Server scope and audience

Before committing to a server boundary, answer: what workflow does this server serve, and who is the audience?

The unit of a server is a user workflow, not an API. A single rich API can earn its own server when the audience is large and the API surface supports a full workflow (PubMed for literature research, SEC EDGAR for financial analysis, Shodan for internet-wide device intelligence). Multiple APIs should collapse into one server when they serve the same workflow from different angles — a "threat intelligence" server that aggregates VirusTotal, AbuseIPDB, and GreyNoise is more useful than three separate servers because the user's goal is "assess this indicator," not "query VirusTotal."

Don't default to one-API-one-server. That's the right call when the API is deep enough and the audience is large enough, but it's not the starting point. The starting point is the workflow:

Signal	Server boundary
Single API with rich surface, large audience	Standalone server named for the platform (pubmed-mcp-server, secedgar-mcp-server)
Multiple APIs serving the same workflow	One server named for the workflow (threat-intel-mcp-server), APIs are internal sources
Domain with distinct sub-audiences	Consider splitting — a pentester and a SOC analyst have different workflows even in the same domain
Pure computation, no external deps	Standalone server named for the capability (calculator-mcp-server, redteam-mcp-server)

When multiple APIs collapse into one server, the tool surface is organized around what the user is doing, not which API gets called. The agent says "investigate this domain" and the server routes to the best available source internally. Individual APIs become service-layer implementation details, not tool-surface identities.

Server Naming

The server name (repo name, npm package, public identity) must communicate what it does at a glance. The test: can a human or agent scanning a server list tell what this server does from the name alone?

• Use the canonical platform/brand name, not abbreviations. libofcongress-mcp-server not loc-mcp-server ("loc" reads as lines-of-code or location). federal-reserve-mcp-server not fred-mcp-server ("fred" reads as a person's name).
• Add a descriptive suffix when the base name is a non-obvious acronym. Pattern: {acronym}-{domain}-mcp-server — e.g., eia-energy-mcp-server, bls-labor-mcp-server, nhtsa-vehicle-safety-mcp-server. Skip when the name is already self-descriptive (earthquake-mcp-server, wikidata-mcp-server).
• The name becomes the tool prefix. Every tool is {prefix}_{verb}_{noun}, so the server name shows up in every tool call an agent sees. A descriptive name gives agents domain context without reading the server's instructions.

Steps

1. Research External Dependencies

Applies when: the server wraps an external API or service. Skip for internal-only servers (computation, local file ops, in-memory state, code analysis utilities) and jump to Step 2.

Before designing, verify the APIs and services the server will wrap. Read the docs, then hit the API — real requests reveal what docs omit.

Research inline by default — fetch docs, read SDK readmes, confirm assumptions before committing them to the design. For each external dependency:

• Fetch API docs, confirm endpoint availability, auth methods, rate limits
• Check for official SDKs or client libraries (npm packages)
• Note any API quirks, pagination patterns, or data format considerations

When research is genuinely parallelizable (multiple independent APIs, several SDKs to evaluate), spawn background agents for the independent legs while you proceed with domain mapping. Skip the overhead for a single API — just read it yourself.

Live API probing. After reading docs, make real requests against the API to verify assumptions:

• Response shapes — confirm actual field names, nesting, and types. Docs frequently lag or omit fields.
• Batch/filter endpoints — look for filter.ids, bulk GET, or query-by-multiple-IDs patterns. A single batch request replaces N individual fetches and eliminates serial-request bottlenecks and rate-limit accumulation.
• Field selection — check if the API supports fields or select parameters to request only the data you need. This reduces payload size dramatically for large objects.
• Pagination behavior — verify token format, page size limits, and what happens when results exceed one page.
• Error shapes — trigger real 400/404/429 responses to see the actual error format, not just what docs claim.
• Unknown-param behavior — send one deliberately misspelled parameter. If the API silently ignores it (plausible but unfiltered results instead of an error), every typo'd or unverified param name becomes a silent-wrongness bug — the service layer then needs a strict allowlist of confirmed spellings, and new filters require a probe before they ship.
• Omission semantics — for each major optional parameter, check what omitting it actually returns. Some APIs default to the intuitive scope; others silently widen (all historical versions, all statuses, global instead of regional). A default that changes result meaning becomes a server-side default plus an echoed output field, not something left to the agent.

Stopping condition: at minimum, probe one list/search endpoint, one single-item GET, one error case (force a 404 or 400), and one unknown-param request. For large APIs with many resource types, add one probe per major noun. Stop when the response shapes and error envelope are confirmed.

This step prevents building a service layer against assumed response shapes that don't match reality.

2. Map User Goals, Then Domain Operations

Start with user goals, not endpoints. Enumerate the outcomes an agent (and its human) will actually try to accomplish with this server — usually 3–10, scaled to domain size. These drive the workflow tools that form the spine of the surface. Endpoint-inventory-first design produces 1:1 API mirrors; goal-first design produces tools agents reach for. For internal-only servers, goals map to capabilities rather than endpoints — e.g., "format markdown to GFM," "tokenize text by model," "compute file hash."

Example user goals for a project management server:

• Find tasks I'm assigned to that are due soon
• Create a task in a project, assign it, and notify the owner
• Mark a task complete and log the outcome
• Audit a project's overdue work

Then enumerate the underlying domain operations the system supports, grouped by noun. These are the raw material workflow tools compose and single-action tools back-fill where workflows don't cover an edge case.

Noun	Operations
Project	list, get, create, archive
Task	list (by project), get, create, update status, assign, comment
User	list, get current

The user-goal list shapes the tool surface; the operation list fills in the gaps. Not every operation becomes a tool — an operation stays as raw material (not its own tool) when it's already fully covered by an existing tool's output, or when the only agents who'd use it are in scenarios outside this server's stated purpose.

3. Classify into MCP Primitives

Tools are the primary interface. Not all MCP clients expose resources — many are tool-only (Claude Code, Cursor, most chat UIs). Design the tool surface to be self-sufficient: an agent with only tool access should be able to do everything the server is built for. Resources add convenience for clients that support them (injectable context, stable URIs), but are not a reliable access path.

Primitive	Use when	Examples
Tool	The default. Any operation or data access an agent needs to accomplish the server's purpose.	Search, create, update, analyze, fetch-by-ID, list reference data
App Tool	Rare — default to a standard tool. Only when a human will actively interact with the result in real time and the target client supports MCP Apps. Most clients are tool-only and most agent workflows are read-by-LLM, not viewed-by-human. App tools add an iframe + CSP, app.ontoolresult/callServerTool plumbing, host-context wiring, and a format() text twin that still has to be content-complete (since most clients only see that). Two surfaces to keep in sync, two failure modes per change.	Dense tabular state a human scrubs through; form-based human approval in an MCP Apps-capable client
Resource	Additionally expose as a resource when the data is addressable by stable URI, read-only, and useful as injectable context.	Config, schemas, status, entity-by-ID lookups
Prompt	Reusable message template that structures how the LLM approaches a task	Analysis framework, report template, review checklist
Neither	Internal detail, admin-only, not useful to an LLM	Token refresh, webhook setup, migrations

What the tool surface needs to cover depends on the server: a read-only research server has different economics than a CRUD project management server. Consider the domain, the expected agent workflows, whether it wraps one API or many, and what data relationships exist. The test is: can a tool-only agent accomplish everything this server is for?

Common traps:

• Data locked behind resources: If something an agent needs is only accessible via a resource, it's invisible to tool-only clients. That data might warrant its own tool, or it might already be covered by an existing tool's output — but it needs a tool path somewhere.
• CRUD explosion: Don't map every REST endpoint to a tool. Related operations on the same noun often belong in one tool with an operation/mode parameter (see Step 4).
• 1:1 endpoint mirroring: API endpoints are designed for programmatic consumers. LLM tools should be designed for workflows — what an agent is trying to accomplish, not what HTTP calls happen under the hood.

Irreversible operations stay in the UI. The "Neither" bucket above covers operations that aren't useful to an LLM. There's a second, sharper reason to exclude something from the tool surface: operations whose failure mode is catastrophic and unrecoverable. Examples span domains — dropping a production database table (data loss across every row), force-emptying a versioned cloud-storage bucket (no recovery once the lifecycle policy fires), revoking the workspace's last admin role (locks everyone out, recovery requires vendor support), GDPR permanent-delete on a customer profile (un-restorable by design), purging an analytics warehouse partition older than the retention window (auditable history gone), or deleting the single audience on a free-plan email platform (nukes every subscriber and historical report in one call). These are useful to an LLM in principle, but the blast radius of a mis-call is disproportionate to any agent workflow. Humans do these in the vendor UI, where confirmation dialogs and undo paths exist. Agents shouldn't have the tool at all.

This is distinct from destructiveHint — that annotation is for operations that are destructive but recoverable (deleting a task, reverting a commit) and agents should still have them. The "stays in the UI" line applies only to operations whose failure is both catastrophic and irreversible.

4. Design Tools

This is the highest-leverage step. Tool definitions — names, descriptions, parameters, output schemas — are the entire interface contract the LLM reads to decide whether and how to call a tool. Every field is context. Design accordingly.

Tool shapes you'll encounter

Most tools follow the {server}_{verb}_{noun} default — one focused responsibility, one clear verb, often (but not always) one upstream call. API-wrapping examples: pubmed_search_articles, pubmed_fetch_articles. Internal-only examples: markdown_format_text, regex_test_pattern, tokens_count_text — same naming convention, no external dep. Two variants warrant explicit design pressures of their own:

Shape	Purpose	Typical form	Examples
Workflow	Multi-step orchestration that replaces a common agent chain	N upstream calls (often parallelized); may elicit confirmation; may need mid-flow cleanup	clinicaltrials_find_studies (search → filter → rank)
Instruction	State-aware procedural guidance — advice, not action	Static markdown + a few live-state fetches, readOnlyHint: true, outputs nextToolSuggestions pre-filling the recommended follow-up. No writes.	git_wrapup_instructions
Reference	Decode opaque domain vocabulary — codes, enums, identifier formats, coverage windows — so agents can build valid inputs for the rest of the surface	Static tables or one cached fetch (often zero upstream calls); consolidate N lists under one topic enum; readOnlyHint: true, openWorldHint: false when offline	medcode_list_systems, osv_list_ecosystems

These aren't boxes every tool must fit into — some blend shapes — but the design pressures differ enough that naming them helps avoid re-discovering the patterns per server. The subsections below cover considerations specific to each — workflow framing applies broadly; instruction tools, reference tools, and workflow safety are their own subsections.

Think in workflows, not endpoints

The unit of a tool is a useful action, not an API call. Ask: "What is the agent trying to accomplish?" — not "What endpoints does the API have?"

A single tool can call multiple APIs internally, apply local filtering, reshape data, and return enriched results. The LLM doesn't know or care about the underlying calls.

// Workflow tool — search + local filter pipeline, not a raw API proxy
const findStudies = tool('clinicaltrials_find_studies', {
  description: 'Matches patient demographics and medical profile to eligible clinical trials. Filters by age, sex, conditions, location, and healthy volunteer status. Returns ranked list of matching studies with eligibility explanations.',
  // handler: listStudies() → filter by eligibility → rank by location proximity → slice
});

Tip — mode consolidation. When a tool has several related operations on the same noun, you can consolidate them under one tool with a mode/operation enum. This affects both naming (noun-led, e.g., github_pull_request) and handler design (dispatch by mode). Use when it tightens the surface; skip when ops diverge enough to warrant separate tools.

Multi-source tools and fallback chains

Applies when: a server aggregates multiple data sources for the same workflow, and the "best" source varies by input type, availability, or coverage. Skip for single-API servers.

When a tool's goal can be served by multiple sources, design it as a multi-source tool — the agent calls one tool, the handler routes to the best source (or fans out to several) internally. This is the difference between a "PubMed wrapper" and a "literature research server": pubmed_search_articles tries PubMed first, falls back to EuropePMC for broader coverage, then Unpaywall for open access. The agent doesn't choose which API to hit — the server makes that decision based on what works.

Two patterns:

Source fallback chains — try sources in priority order, fall through on failure or empty results. Best when sources cover the same data with different depth or availability. The output should indicate which source provided the data so the agent (and human) can assess provenance.

// Handler pseudocode — not a real implementation
async handler(input, ctx) {
  // Primary: PubMed E-utilities (authoritative, best metadata)
  const result = await pubmedService.search(input.query);
  if (result.items.length > 0) return { ...result, source: 'pubmed' };

  // Fallback: EuropePMC (broader coverage, includes preprints)
  const epmcResult = await epmcService.search(input.query);
  if (epmcResult.items.length > 0) return { ...epmcResult, source: 'europepmc' };

  return { items: [], source: 'none', message: 'No results from any source.' };
}

Multi-source fan-out — query multiple sources in parallel, merge results. Best when sources provide complementary data about the same entity. Use Promise.allSettled so one failing source doesn't tank the whole call.

// Handler pseudocode — indicator enrichment across threat intel sources
async handler(input, ctx) {
  const [vt, abuse, greynoise] = await Promise.allSettled([
    vtService.lookup(input.indicator),
    abuseIpService.check(input.indicator),
    greynoiseService.query(input.indicator),
  ]);
  return {
    indicator: input.indicator,
    sources: {
      virustotal: vt.status === 'fulfilled' ? vt.value : { error: vt.reason.message },
      abuseipdb: abuse.status === 'fulfilled' ? abuse.value : { error: abuse.reason.message },
      greynoise: greynoise.status === 'fulfilled' ? greynoise.value : { error: greynoise.reason.message },
    },
    // Server synthesizes a verdict from available data — the agent gets a conclusion, not raw API dumps
    assessment: synthesizeVerdict(vt, abuse, greynoise),
  };
}

In both patterns, the tool surface is organized around what the user is doing. Sources are service-layer details — the agent sees threat_enrich_indicator, not virustotal_lookup + abuseipdb_check + greynoise_query. Mode-based dispatch by input type (e.g., indicator_type: 'ip' | 'domain' | 'hash') naturally routes to different source chains per mode, since different sources cover different indicator types.

There is no fixed ceiling on tool count — tools need to earn their keep, but don't artificially limit the surface. If the domain genuinely has 20 distinct workflows, expose 20 tools.

Cut the surface

After mapping tools, review the full list critically. A tool that covers a niche use case, serves a tiny fraction of agents, or duplicates what another tool already handles is a candidate for deferral. Drop it from the design and note it as a future addition if demand warrants. Every tool in the surface is cognitive load for tool selection — a tight surface outperforms a comprehensive one.

Instruction tools

Applies when: the domain has recurring "how do I do X well given my current state" questions worth merging with static procedural content. Skip otherwise.

Some domains benefit from a tool whose output is guidance, not data — a markdown playbook tailored by live account state, with pre-filled next-step tool calls. These sit between Prompts (static templates, client-invokable) and action tools (do work, return data): they return advice, but the advice is worth more than static text because it merges procedural content with the agent's actual situation.

Characteristics:

• Output is markdown guidance, not structured data (though the output schema still has fields — typically guidance, diagnostics, and nextToolSuggestions)
• Merges static procedural content with live state — the value is the tailoring. "You have 12 staged files spanning 4 unrelated changes — split them into separate commits before pushing" beats a generic best-practices article. The same shape works in other domains: "Your slowest query is 2.3s on orders.customer_id — add the index before tuning the planner" (database advisor), "Error rate spiked 4× at 14:32 UTC, 4 minutes after the web@a3f9c2 deploy — roll back before chasing the upstream provider" (incident triage).
• readOnlyHint: true, openWorldHint: false — no writes, deterministic given the same inputs and account state
• Outputs nextToolSuggestions — an array of recommended follow-up tool calls with arguments pre-filled from the diagnostics, not just tool names. The agent consumes the playbook, then executes steps with other tools.
• Consolidate by topic enum — what could be N separate per-topic tools collapses into one

const wrapupInstructions = tool('git_wrapup_instructions', {
  description: 'Procedural guidance tailored to current repo state. Returns best-practice markdown merged with live diagnostics (staged/unstaged files, branch info, recent commits) and pre-filled follow-up tool calls. Read-only; the agent then executes steps with other tools.',
  annotations: { readOnlyHint: true, openWorldHint: false },
  input: z.object({
    topic: z.enum(['review-changes', 'stage-and-commit', 'push-to-remote'])
      .describe('Playbook topic. Determines which static guidance is returned and which live state is fetched for tailoring.'),
  }),
  output: z.object({
    guidance: z.string()
      .describe('Markdown playbook content, tailored to current account state.'),
    diagnostics: z.record(z.unknown())
      .describe('Live state used to tailor the guidance (e.g., staged file count, branch divergence, recent commit cadence).'),
    nextToolSuggestions: z.array(z.object({
      toolName: z.string().describe('Tool to call next.'),
      reason: z.string().describe('Why this step is recommended given current state.'),