Tessera's MCP server surfaces LLM cost optimization decisions directly in your AI editor. Install it in Claude Desktop, Cursor, or Cline, pass a TESSERA_API_KEY, and you get six tools: list workloads with their anchor costs, pull savings reports, check queued recommendations with expected lift, browse audit-immutable ledger entries, view quality snapshots with drift events, and approve a mechanic to move it from suggested to active. The read tools let agents diagnose spend, the single write tool lets them act on recommendations with an audit trail. It's designed for teams routing LLM calls through Tessera's proxy and need agents to surface what's drifting or where to switch providers without opening the dashboard.
The MCP server that returns money, not data.
Status: v0.1.3 — published 2026-05-27 on npm with sigstore SLSA provenance v1, listed on registry.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 an MCP server 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 returns savings 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.
npx @tessera-llm/mcp-server
Or add to your client config:
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"tessera": {
"command": "npx",
"args": ["-y", "@tessera-llm/mcp-server"],
"env": {
"TESSERA_API_KEY": "tk_..."
}
}
}
}
Claude Code (.mcp.json in project root):
{
"mcpServers": {
"tessera": {
"command": "npx",
"args": ["-y", "@tessera-llm/mcp-server"],
"env": {
"TESSERA_API_KEY": "tk_..."
}
}
}
}
Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"tessera": {
"command": "npx",
"args": ["-y", "@tessera-llm/mcp-server"],
"env": { "TESSERA_API_KEY": "tk_..." }
}
}
}
Get a TESSERA_API_KEY at tesseraai.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.
| Tool | Read/Write | Purpose |
|---|---|---|
tessera_list_workloads | read | List your mapped workloads with anchor cost + current m-stack. |
tessera_get_savings_report | read | Anchored spend + measured savings for a window. |
tessera_get_recommendation_queue | read | Pending Optimize-tab recommendations with expected lift + confidence. |
tessera_get_ledger_entries | read | Audit-immutable Monthly Reading rows (provider call, mechanic stack applied, savings). |
tessera_get_quality_snapshot | read | SLA floor + p50/p95 quality scores + drift events. |
tessera_approve_recommendation | mutate | Move a queued mechanic from "suggested" to "active" with audit-trail entry. |
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.
TESSERA_MCP_TRANSPORT=http to bind on localhost:8788 for remote / Goose / Zed-via-mcp-remoteSSE (deprecated in MCP spec 2025-11-25) is not supported.
TESSERA_API_KEY env var or Authorization: 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).
__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.execute_code escape hatch. Typed verbs only.Apache-2.0. Tessera is a product of Fintechagency OÜ (Estonia, Tallinn).
TESSERA_API_KEY*secretAPI key in tk_* format. Get one free at https://tesseraai.io/dev.
TESSERA_UPSTREAM_API_BASE_URLdefault: https://ledger.tesseraai.ioOverride only for staging or local-dev testing.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent