Skip to main content
Glama
skeeved

wordle-mcp

by skeeved
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

wordlebot

An MCP server that helps solve Wordle. You tell it which letters were hits, misses, or in the wrong spot; it returns five-letter words consistent with every clue, best guesses first.

What it does

  • suggest_words — give it your guess history (each word + the tile colors) and it returns every accepted word still consistent with the clues, ranked by a letter-frequency heuristic.

  • starting_words — strong opening guesses.

  • validate_word — is a word accepted by Wordle?

  • wordle://wordlist/metadata (resource) — provenance of the bundled word list.

Related MCP server: LeetCode MCP Server

The word list (data source & honesty caveat)

The bundled list is 14,855 five-letter words: the set of accepted guesses, sourced from the public tabatkins/wordle-list repository, which extracts them straight from Wordle's own source code. It's normalized (lowercased, de-duplicated, sorted, every entry validated as exactly five ASCII letters) and shipped as a static file with a SHA-256 checksum and retrieval date in src/wordle_mcp/data/words.meta.json.

Caveat, stated plainly: since the NYT acquisition, the daily-answer subset has drifted — words are played out of original order, some have repeated, and some new answers were never on the original list. So no static list perfectly mirrors NYT's live answer set. For a constraint solver this is fine: we filter accepted words against your clues. But the ranking is a heuristic for a strong guess, not a probability of being today's answer.

To refresh the list from source at any time:

python scripts/refresh_wordlist.py

Install

Requires Python 3.10+.

git clone https://github.com/skeeved/wordlebot && cd wordlebot
python -m venv .venv && source .venv/bin/activate
pip install -e .

(Or, with uv: uv sync.)

Connect it to Claude Desktop

The server is a local stdio MCP server, so Claude Desktop can launch it directly. The simplest setup is to install the package into a virtual environment and point Claude at the generated console script.

1. Install the package

From the repository root:

python -m venv .venv
source .venv/bin/activate
pip install -e .

2. Add the server to Claude Desktop

Open Claude Desktop Settings → Developer → Edit Config and add or update ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) with an absolute path:

{
  "mcpServers": {
    "wordlebot": {
      "command": "/<path>/wordlebot/.venv/bin/wordlebot"
    }
  }
}

If you prefer not to activate the virtual environment, run it through uv instead:

{
  "mcpServers": {
    "wordlebot": {
      "command": "uv",
      "args": ["--directory", "/<path>/wordlebot", "run", "wordlebot"]
    }
  }
}

Then fully quit and relaunch Claude Desktop. If the connection is successful, Claude should show an MCP server indicator and expose the server's tools.

3. Test it interactively

To try the server outside of a host app, use the MCP Inspector:

npx @modelcontextprotocol/inspector wordlebot

Connect it to VS Code

VS Code can also use this server through its MCP configuration file. The easiest approach is to create or edit .vscode/mcp.json in your workspace (or use the Command Palette command MCP: Open User Configuration).

Example workspace configuration:

{
  "servers": {
    "wordlebot": {
      "type": "stdio",
      "command": "/<path>/wordlebot/.venv/bin/wordlebot"
    }
  }
}

Or, if you want VS Code to launch it through uv:

{
  "servers": {
    "wordle-solver": {
      "type": "stdio",
      "command": "uv",
      "args": ["--directory", "/<path>/wordlebot/.venv/bin", "run", "wordlebot"]
    }
  }
}

After saving the file, VS Code will usually prompt you to trust and start the server. Once it is running, the tools should appear in chat and agent workflows.

How to describe feedback

Each guess is a word plus a 5-character pattern, left to right:

Symbol

Meaning

G

green — correct letter, correct spot

Y

yellow — letter is in the word, wrong spot

B

gray/black — letter not in the word

(2/1/0 and . x _ are also accepted as G/Y/B.)

Example call to suggest_words:

{
  "guesses": [
    { "word": "crane", "feedback": "BGGGB" },
    { "word": "trail", "feedback": "BGGBB" }
  ],
  "max_results": 10
}

→ returns { "total_matches": 18, "words": ["grans", "brank", ... , "prank", ...], ... }

In practice you just talk to your MCP host: "I played CRANE and got gray-green-green-green-gray, then TRAIL and got gray-green-green-gray-gray. What should I try?" — the host fills in the tool call.

The one subtle rule: duplicate letters

A gray tile does not always mean "letter absent." If you guess a word with two of a letter but the answer has only one, one copy comes back colored and the other gray — the gray means "no more copies," not "none at all."

Analogy: requesting two ocean-view rooms at a hotel with only one. The desk confirms one and declines the other; the decline doesn't mean zero ocean-view rooms exist — just none beyond the one you got.

The solver implements this exactly: green + yellow tiles set a minimum count for a letter; any gray tile for that same letter turns the minimum into an exact count. This is verified by a property test (tests/test_solver.py::test_matches_equals_reference) that checks the matcher against a from-scratch implementation of Wordle's real feedback rule across hundreds of thousands of answer/guess/candidate combinations.

Development

pip install -e ".[dev]"
pytest -q

Notes on the MCP SDK

Built on the v1.x MCP Python SDK (mcp[cli], FastMCP), which is the stable, production-recommended line. It is pinned >=1.27,<2: SDK v2 (targeting the 2026-07-28 spec) renames FastMCP to MCPServer and moves to a stateless request/response protocol. When you migrate, the tool functions here carry over unchanged; only the server bootstrap in src/wordle_mcp/server.py needs updating per the SDK migration guide.

License

GPL-3.0-only.

Available Tools

3 tools
starting_wordsB

Suggest strong opening guesses (words rich in common, distinct letters).

ParametersJSON Schema
NameRequiredDescriptionDefault
max_resultsNo

TDQS

B3.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds relevant context by explaining that the guesses are 'rich in common, distinct letters,' giving insight into the output's nature. However, it does not disclose the return format (e.g., a list of strings), language constraints, or how max_results affects the behavior. It is partially transparent but lacks completeness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose. It contains no filler or redundant information, making it appropriately concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description provides a basic understanding of its purpose and the nature of its suggestions. However, it does not specify the return format, the word source, or how it relates to sibling tools, leaving some gaps in context for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only the parameter name 'max_results' with a default of 15 and no description. The tool description does not mention this parameter at all, so it adds no explicit meaning beyond the schema. There is an implied connection between 'strong opening guesses' and limiting results, but the description fails to clarify the exact role of max_results.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: suggesting strong opening guesses. It uses the specific verb 'suggest' and identifies the resource as guesses for starting words. It distinguishes itself from siblings by focusing on 'opening guesses' rather than general word suggestions or validation, though it could be more explicit about the word game context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus the sibling tools suggest_words or validate_word. The description implies it is for opening guesses, but it does not clarify when to choose this over alternatives, nor does it provide any exclusions or prerequisites. The agent is left to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

suggest_wordsA

Return five-letter words consistent with all your guesses so far.

Pass every guess you've made this game together with the tile colors Wordle showed. Results are ranked by a positional letter-frequency heuristic (strong next guesses first). With no guesses, you get recommended opening words.

Correctly handles duplicate letters: a gray tile for a letter you also got green/yellow means "no more copies", not "letter absent".

ParametersJSON Schema
NameRequiredDescriptionDefault
guessesYes
max_resultsNo

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does a good job: it discloses the ranking heuristic, the opening-word fallback, and the subtle duplicate-letter handling. This is substantive behavioral context that goes beyond the name and schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the core purpose. Each sentence adds meaningful detail—usage, ranking, and an important edge case—without waste or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema and no annotations, the description covers the essential context: what the tool does, how to pass inputs, ranking behavior, no-guess behavior, and duplicate handling. It doesn't mention what happens if no words match or the exact return format, but these are minor gaps for a suggestion tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for top-level parameters, so the description compensates by explaining what 'guesses' should contain (all guesses plus tile colors) and how feedback is interpreted. It does not address 'max_results', but that parameter is relatively self-explanatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's primary function: returning five-letter words consistent with prior guesses. It distinguishes itself from siblings by focusing on guess-consistency, while the no-guess fallback to opening words is clearly described.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit instructions on when to use the tool: pass every guess with the tile colors Wordle showed. It also clarifies behavior when no guesses exist, but it doesn't explicitly mention alternatives like 'starting_words' or 'validate_word' for comparison.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

validate_wordA

Check whether a 5-letter word is accepted as a Wordle guess.

ParametersJSON Schema
NameRequiredDescriptionDefault
wordYes

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavior. It indicates a read-only validation operation via 'Check', but doesn't detail edge cases, case sensitivity, or the exact return type. This is minimal but not misleading.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that gets straight to the point. No unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool (one parameter, no output schema), the description is sufficient for understanding the tool's purpose and parameter constraint. It could mention return format, but the verb 'Check' implies a boolean answer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema only defines 'word' as a string with no description. The tool description adds key constraints: the word must be 5 letters and is a Wordle guess. This compensates for the 0% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool validates a word against Wordle's accepted guesses. It uses the specific verb 'Check' and names the resource, distinguishing it from sibling tools that suggest or start words.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for verifying whether a specific word is a valid Wordle guess. It doesn't explicitly mention when not to use it or alternatives, but the context of validation versus suggestion is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv0.1.0
    • First observedstarting_words
    • First observedsuggest_words
    • First observedvalidate_word
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation4/5

suggest_words and starting_words both recommend words, but suggest_words is for any point in the game while starting_words specifically targets openings, and validate_word is clearly distinct. The slight overlap when no guesses are given is clarified by descriptions.

Naming Consistency4/5

Tool names mostly follow a verb_noun pattern (suggest_words, validate_word), but starting_words deviates by using an adjective/participle. Overall the pattern is readable and predictable.

Tool Count5/5

Three tools is a well-scoped set for a Wordle helper server, covering the essential actions without redundancy or bloat.

Completeness5/5

The tool set covers the core needs: opening suggestions, ongoing guess feedback, and word validation. No obvious gaps for the stated purpose.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/skeeved/wordlebot'

If you have feedback or need assistance with the MCP directory API, please join our Discord server