Tessera MCP Server

by tesseraai.io·io.tesseraai/mcp-server·v0.1.2·4 stars

No reviews yet

MCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations.

C69/100grade C

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

C69/100

full report

Adoption

Growing

4 stars36 downloads/wk

Reviews

Write one

Nobody has reviewed Tessera MCP Server yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Tessera MCP Server tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

tessera_approve_recommendation
Approve a pending recommendation \u2014 transitions it from "open" to "in_progress" and appends an approval line (with the approving session's API key prefix) to the recommendation notes. THIS IS THE ONLY MUTATING TOOL IN v0.1. Provider config changes, API key management, composition cap changes, and Stripe operations are deliberately not exposed here \u2014 those live in the dashboard where blast
tessera_get_ledger_entries
Return audit-immutable Monthly Reading rows for a workload since a given timestamp. Each entry records the provider call (e.g. openai/gpt-4o-mini-2024-07-18), the mechanic stack applied (e.g. ["M1", "M3", "M5"] for auto-route + auto-compress + auto-cache), anchor cost (baseline pricing before Tessera optimization), actual cost (post-optimization), and the delta savings in USD. Anchor cost referenc
tessera_get_quality_snapshot
Return the quality snapshot for a workload \u2014 SLA floor (default 0.95) and measured p50 / p95 quality scores from canary evaluations over the chosen window. Null p50 / p95 means there were no canary samples in the window. Quality is the primary trust factor \u2014 savings without quality verification is not Tessera surface.
tessera_get_recommendation_queue
Return open Optimize-tab recommendations \u2014 proposed actions (routing changes, caching switches, batching, etc) that Tessera suggests for a workload. Each carries a family classification, human-readable title and description, an estimated monthly savings range in USD (low / mid / high), engineering days to implement, reversibility, output-quality risk level, status, and priority (lower = highe
tessera_get_savings_report
Return the savings report for a single workload over a chosen window. Compares anchor (baseline) spend against actual spend after Tessera optimizations, reports measured savings in USD and percent, and shows the performance fee accrued (20% of measured savings on Production plan, 0% on Free Sandbox). Audit-immutable \u2014 every number traces to ledger entries via tessera_get_ledger_entries.
tessera_list_workloads
List the mapped workloads in the current Tessera workspace. Each workload represents a category of LLM calls (e.g. "support-triage", "summarisation", "ranker-prompt") with its target provider, model id, and scope status. Use this as the entry point before drilling into savings, recommendations, ledger entries, or quality snapshots for a specific workload. Returns no secrets and no prompt content.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan11 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitystatic API keys via environment variables6/15
Maintenancelast push 113 days ago8/15
Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10

Overall 69/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Tessera MCP Server compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 69/100; higher than 35% of 4,460 AI and agents servers
Tools: 6; the typical AI and agents server has 6
Tools that change things: 0%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 4; more than 77% of 2,711 AI and agents servers
Downloads a week: 36; more than 27% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read

Install Tessera MCP Server in Claude Code, Cursor or VS Code

Runs npx -y @tessera-llm/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp-server -- npx -y @tessera-llm/mcp-server

Add to Cursor

What the publisher says

From the Tessera MCP Server repository's README, as published. We do not edit it. Read it on GitHub

tessera-mcp-server

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.

See it in action

▶ 41-second walkthrough: live counter ticks · baseline $74,800 → actual $30,000 ($44,800 saved, 60% reduction) · audit-immutable savings ledger. Click to play.

Install

npx @tessera-llm/mcp-server

Or add to your client config:

Claude Desktop (~/Library/Application Support/Claude/claudedesktopconfig.json on macOS, %APPDATA%\Claude\claudedesktopconfig.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 TESSERAAPIKEY at tesseraai.io/dev — Free Sandbox is 60M tokens/month with no card.

Tools

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.

Transport

stdio (default) — local clients (Claude Desktop, Cursor, Cline, Continue, Claude Code)
Streamable HTTP (optional) — set TESSERAMCPTRANSPORT=http to bind on localhost:8788 for remote / Goose / Zed-via-mcp-remote

SSE (deprecated in MCP spec 2025-11-25) is not supported.

Auth

TESSERAAPIKEY env var or Authorization: Bearer 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).

Security posture

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Tessera MCP Server: common questions

Is Tessera MCP Server safe?: With care: it is graded C, so read the findings first (69/100). Read the Tessera MCP Server safety report
How do I install Tessera MCP Server?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Tessera MCP Server need an API key?: Yes. The registry entry asks for TESSERA_API_KEY.
Is Tessera MCP Server maintained?: The last commit was 151 days ago (2026-06-06). The latest release is v0.1.2.
What can I use instead of Tessera MCP Server?: Servers from other publishers that do the same job: agent-device MCP server, Image MCP server and Agent Recall MCP server.
How does Tessera MCP Server compare with other AI and agents MCP servers?: safety score 69/100 (higher than 35% of 4,460 AI and agents servers); tools 6 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Tessera MCP Server

Same job from other publishers: the closest match first, then the best rated.

agent-device
Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
not reviewed
Widely used
A
Image
AI image generation and editing with prompt optimization and quality presets
not reviewed
Established
B
Agent Recall
Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
not reviewed
Established
A
llmtrim
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
not reviewed
Established
A
three.ws Autopilot
Set autopilot scopes and a daily SOL spend cap, then propose, execute, and undo agent actions.
not reviewed
Established
B

Run it through the gateway

Local package. It runs on your machine, not through the gateway.

Rating: —
Safety grade: C · 69/100
Stars: 4
Downloads/wk: 36
Price: Free
Licence: Apache-2.0
Transport: Local · npm
Version: 0.1.2
Category: AI and agents
Last release: 2026-06-06

Credentials it needs

TESSERA_API_KEYsecretAPI key in tk_* format. Get one free at https://tesseraai.io/dev.
TESSERA_UPSTREAM_API_BASE_URLOverride only for staging or local-dev testing.

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/tesseraai-mcp-server.svg)](https://mcp.market/server/tesseraai-mcp-server)

How the badge works