Tessera MCP Server
About
MCP server for Tessera's LLM cost-optimization layer. Anchored spend, drift detection, recommendations as typed tools.
Details
- Author
- tessera-llm
- Downloads
- 391
- Categories
- Developer Tools, AI, Infrastructure, Other
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Tessera MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Obtain a free API key from tesseraai.io/dev (no credit card required) and set it as the TESSERA_API_KEY environment variable. The server runs over stdio by default; to use Streamable HTTP instead, set TESSERA_MCP_TRANSPORT=http.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"tessera mcp server": {
"tessera": {
"command": "npx",
"args": [
"-y",
"@tessera-llm/mcp-server"
],
"env": {
"TESSERA_API_KEY": "tk_..."
}
}
}
}
}
McpServers
{
"tessera": {
"command": "npx",
"args": [
"-y",
"@tessera-llm/mcp-server"
],
"env": {
"TESSERA_API_KEY": "tk_..."
}
}
}
MCP server for Tessera's LLM cost-optimization layer. Anchored spend, drift detection, recommendations as typed tools.
The MCP server that returns money, not data.
Status:v0.1.3 — published 2026-05-27 on npm with sigstore SLSA provenance v1, listed onregistry.modelcontextprotocol.io.
Tessera is an LLM proxy that optimizes API spend through multi-provider routing, prompt compression, audit-immutable logging, output-length prediction, and batch arbitrage. This package exposes Tessera as anMCPserver for tool-using agents — Claude Desktop, Claude Code, Cursor, Cline, Continue, Goose, Zed.
Where other LLM-infrastructure MCP servers return logs, traces, or prompt metadata, this one returnssavings decisions: what's drifting, what to switch, what to approve, what to audit.
▶ 41-second walkthrough: live counter ticks · baseline $74,800 → actual $30,000 ($44,800 saved, 60% reduction) · audit-immutable savings ledger. Click to play.
Claude Desktop(~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS,%APPDATA%\Claude\claude_desktop_config.jsonon Windows):
{ "mcpServers": { "tessera": { "command": "npx", "args": ["-y", "@tessera-llm/mcp-server"], "env": { "TESSERA_API_KEY": "tk_..." } } } }
Claude Code(.mcp.jsonin project root):
{ "mcpServers": { "tessera": { "command": "npx", "args": ["-y", "@tessera-llm/mcp-server"], "env": { "TESSERA_API_KEY": "tk_..." } } } }
{ "mcpServers": { "tessera": { "command": "npx", "args": ["-y", "@tessera-llm/mcp-server"], "env": { "TESSERA_API_KEY": "tk_..." } } } }
Get aTESSERA_API_KEYattesseraai.io/dev— Free Sandbox is 60M tokens/month with no card.
v0.1 exposes 6 tools (5 read + 1 mutate). Hard cap — no tool sprawl.
Provider config writes, API-key management, composition cap changes, and Stripe operations are deliberately NOT in this surface — they live in the dashboard, where blast-radius requires explicit modal confirmation.
- stdio(default) — local clients (Claude Desktop, Cursor, Cline, Continue, Claude Code)
- Streamable HTTP(optional) — setTESSERA_MCP_TRANSPORT=httpto bind onlocalhost:8788for remote / Goose / Zed-via-mcp-remote
SSE (deprecated in MCP spec 2025-11-25) is not supported.
TESSERA_API_KEYenv var orAuthorization: Bearer <key>header (HTTP transport). Same API key as the SDK —tk_*format. Future v0.2: OAuth 2.1 (aligned with MCP spec RC 2026-07-28).
- Tools receiving user-controlled content (ledger notes, recommendation rationale strings, workload names) are labelled__untrusted__to prevent prompt-injection cascade per the Supabase/Cursor 2025 pattern.
- mcp-scan(Invariant Labs) runs in CI to catch tool-poisoning attacks in tool descriptions.
- Noexecute_codeescape hatch. Typed verbs only.
- No session-based auth. Every request authenticates independently per MCP spec 2026 requirement.
Apache-2.0. Tessera is a product ofFintechagency OÜ(Estonia, Tallinn).
- Tessera landing:tesseraai.io
- Free Sandbox signup:tesseraai.io/dev
- How it works:tesseraai.io/how-it-works
- MCP protocol spec:modelcontextprotocol.io
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
An MCP server for fetching conversation history and prompts from the LangSmith observability platform.
Crowdsourced MCP server reliability scoring — 615+ servers monitored, 2.17M+ health checks, real-time reliability data
MCP server that predicts your monthly LLM spend from local Claude Code / Cursor / Codex logs. Forecasts end-of-month $, ranks spike drivers, warns before budget breach. Free tier + paid tier ($19/mo), MIT licensed.
MCP server for AI agent token-cost telemetry + quota-window awareness across Anthropic, OpenAI, Gemini, Ollama, AWS Bedrock. Per-agent attribution, spend-spike detection, 429-prediction tools.
An MCP server for interacting with the SeaLights platform for quality intelligence.
Tickerr — Live AI Tool Status & API Pricing
Real-time status monitoring, uptime tracking, incident history, and API pricing for 42+ AI tools including ChatGPT, Claude, Gemini, Cursor, GitHub Copilot, Perplexity, DeepSeek, and Groq. No API key required. Data updated every 5 minutes from independent monitoring infrastructure.
A comprehensive Model Context Protocol (MCP) server for the Cloudability API, providing advanced cost management, Kubernetes container analytics, and budget forecasting capabilities.
GA4 conversion analyst inside Claude. Ask where your funnel is leaking, get numbers back.
Connect GA4 to Claude or ChatGPT via Two Minute Reports MCP. Track New Users, Sessions, and Signups to improve website performance.
MCP server for Langfuse — query traces, debug errors, analyze sessions and prompts from any AI agent
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




