AbliteratedLLM MCP server
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
AbliteratedLLM MCP server
@abliteratedllm/mcp-server is a Model Context Protocol server for AbliteratedLLM, a pay-per-token, OpenAI-compatible API for abliterated (refusal-removed) and stock open-weight models. It lets an MCP host such as Claude Desktop, Claude Code, Cursor or VS Code list the models and their prices, estimate what a request will cost, check your balance, and send a prompt to a model.
The server runs on your machine over stdio. Your API key stays in your MCP host's configuration and is sent only to https://api.abliteratedllm.dev.
Tools
Tool | What it does | API key | Spends credit |
| Lists the models in the public catalog: id, name, variant, context length, max output tokens, input types, and prices in USD per 1M tokens (input, output, cached input, priority tier where offered). Optional filters: | no | no |
| Prices token counts you supply with the catalog prices and the API's billing formula, rounded up to $0.000001 like billing. Inputs: | no | no |
| Shows the balance of the account that owns the key, the credit held by running requests, whether it is a trial account, and what is left of the key's daily, monthly and lifetime spend caps. Amounts are decimal strings, exactly as the API sends them. It is also the way to check that a key works. | yes | no |
| Sends a | yes | yes |
Notes:
variant: "abliterated"means the model's refusal behavior was removed from its weights. Models withvariant: "stock"are the vendors' original weights.chatis text only and returns one non-streamed reply. It does not pass tools to the model.This server has no tokenizer.
estimate_costprices the counts you give it, so its result is an estimate. Reasoning tokens are output tokens.The catalog is fetched from
GET https://api.abliteratedllm.dev/v1/modelswithout a key and reused for 5 minutes.
Related MCP server: rapidrouter-mcp
Requirements
Node.js 20.3 or later, which includes
npx.For
chatandget_balance: an API key from abliteratedllm.dev/dashboard/keys. Keys start withsk-. A key with a daily spend cap is recommended; caps are set on the same page.
list_models and estimate_cost work without a key.
Setup
Each snippet starts the server with npx -y @abliteratedllm/mcp-server. Replace sk-... with your key, and keep it out of files you commit or share.
Claude Code
claude mcp add --scope user --env ABLITERATEDLLM_API_KEY=sk-... abliteratedllm -- npx -y @abliteratedllm/mcp-server--scope user saves the server in your user configuration rather than in a project's .mcp.json. Run /mcp in Claude Code to check that it is connected.
To share the server in a project's .mcp.json without the key, let Claude Code expand the variable from your environment:
{
"mcpServers": {
"abliteratedllm": {
"command": "npx",
"args": ["-y", "@abliteratedllm/mcp-server"],
"env": { "ABLITERATEDLLM_API_KEY": "${ABLITERATEDLLM_API_KEY}" }
}
}
}Claude Desktop
Open Settings → Developer → Edit Config, which opens claude_desktop_config.json, and add:
{
"mcpServers": {
"abliteratedllm": {
"command": "npx",
"args": ["-y", "@abliteratedllm/mcp-server"],
"env": { "ABLITERATEDLLM_API_KEY": "sk-..." }
}
}
}Restart Claude Desktop. On Windows, if the server does not start, use "command": "cmd" with "args": ["/c", "npx", "-y", "@abliteratedllm/mcp-server"].
Cursor
Add the server to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json in a project:
{
"mcpServers": {
"abliteratedllm": {
"command": "npx",
"args": ["-y", "@abliteratedllm/mcp-server"],
"env": { "ABLITERATEDLLM_API_KEY": "sk-..." }
}
}
}Prefer the file in your home folder, so the key does not end up in a repository.
VS Code
Run MCP: Open User Configuration from the Command Palette (or create .vscode/mcp.json in a workspace) and add:
{
"inputs": [
{
"type": "promptString",
"id": "abliteratedllm-api-key",
"description": "AbliteratedLLM API key",
"password": true
}
],
"servers": {
"abliteratedllm": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@abliteratedllm/mcp-server"],
"env": { "ABLITERATEDLLM_API_KEY": "${input:abliteratedllm-api-key}" }
}
}
}VS Code asks for the key when the server first starts and stores it, so the key is not written into mcp.json. The tools are available in Chat's agent mode.
Other hosts
Any MCP host that runs local stdio servers works: command npx, arguments -y @abliteratedllm/mcp-server, and the environment variables below.
Configuration
Variable | Default | Description |
| none | Your API key. Needed for |
|
| How long |
Costs and limits
chatspends your prepaid AbliteratedLLM credit. Each reply comes with its token usage and an estimated cost: usage times the catalog prices this server fetched. It is labelled as an estimate.chatalways sendsmax_tokens, 2048 unless you pass another value. Without it the API would use 16384. While a request runs, its wholemax_tokensbudget is held against your balance and the key's spend caps, so a large budget can be refused by a capped key even if the reply would be short. Reasoning tokens count towardmax_tokensand are billed at the output price.reasoning_effortdefaults tolow, which keeps replies faster and cheaper. If a reply comes back empty because reasoning used the whole budget,chatsays so; raisemax_tokensor lowerreasoning_effort.Trial accounts (before the first top-up) allow 1 request at a time and 10 requests per minute per key, and cap output at 4096 tokens per request. See Rate limits and trial.
API errors come back as tool errors with the API's code and what to do about it: a rejected key, low balance (
insufficient_balance), a spend cap (key_spend_cap_reached), rate limits and busy models (with theRetry-Aftertime). The server does not retry on its own.Your MCP host decides when to call tools. Most hosts ask before running a tool; keep that approval on for
chat, since it spends credit.
Prices: abliteratedllm.dev/pricing, or call list_models.
Timeouts
chat waits for one complete reply. Many MCP hosts, including Claude Desktop, Cursor and others that keep the MCP SDK's default, stop a tool call after 60 seconds. So by default the server stops waiting after 55 seconds and returns an explanation instead of a bare host timeout.
A request that is stopped is billed for its estimated input and any output the model generated before it stopped. Keep max_tokens and reasoning_effort modest, or pick a faster model, if replies take long.
If your host allows longer tool calls, raise ABLITERATEDLLM_TIMEOUT_SECONDS, up to 600 (the API's own limit per request is 10 minutes). Claude Code's CLI, for example, waits much longer than 60 seconds by default (see its MCP_TOOL_TIMEOUT setting):
claude mcp add --scope user --env ABLITERATEDLLM_API_KEY=sk-... --env ABLITERATEDLLM_TIMEOUT_SECONDS=300 abliteratedllm -- npx -y @abliteratedllm/mcp-serverWhile chat waits, it sends a progress notification every 10 seconds to hosts that request progress.
The server also handles the API's long-request format: a non-streaming response still running after 90 seconds starts with status 200 and newlines, and an error after that point arrives inside the 200 body. The server checks the body for an error member whatever the status.
Privacy
chatsends your prompt, messages and system prompt tohttps://api.abliteratedllm.dev.get_balancesends only the key.list_modelsandestimate_costsend no key and no prompt.AbliteratedLLM does not store prompts or outputs; see Privacy for the scope.
The server writes no files and keeps nothing between runs. It logs one startup line to stderr, which never includes the key.
AbliteratedLLM is for adults (18+). Its acceptable use policy applies to everything you send.
Development
npm install
npm run build # compile src/ to dist/
npm test # unit tests (node:test; needs Node 22.18 or later to run the TypeScript tests directly)
npm run typecheck # type-check src/ and test/
npm run smoke # start dist/index.js over stdio without a key: tools/list, list_models, estimate_cost, get_balance refusalnpm run smoke reads the public catalog, so it needs network access but no key. With a key in ABLITERATEDLLM_API_KEY, npm run smoke -- --live also calls get_balance and sends one small chat request, which spends a little credit.
To try the tools by hand, the MCP Inspector works too: npx @modelcontextprotocol/inspector node dist/index.js.
Links
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Related MCP Servers
- -licenseCqualityNot gradedmaintenanceEnables interaction with OpenAI-compatible APIs (like Ollama) through MCP tools. Provides access to chat completions, model listings, and embeddings generation from local or remote OpenAI-style endpoints.3-
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to search the Rapid Router model catalog, view prices in USD and INR, send chat completions, and check credit balances through an OpenAI-compatible API.MIT

GPTProto MCPofficial
AlicenseAqualityCmaintenanceEnables AI hosts to discover GPTProto models, retrieve live pricing, make documented API requests, submit custom generations, and poll asynchronous tasks through local MCP tools.917 npmMIT- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to browse and compare model catalogs, pick models by budget or context window, and run completions metered to the caller's own API key.MIT