MCP.Market

Agent Booster MCP server

by sseshachala·io.github.sseshachala/agent-booster·v0.6.4·2 stars
No reviews yet

Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

2 stars128 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Booster yet.

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

Agent Booster tools (6)

write = sends, deletes, buys or posts

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

  • expand_calls

    Return immediate callers or callees of a symbol. Name-based resolution (~70% accuracy on Python).

  • get_symbols

    Return all indexed symbols for a given file path.

  • route_model

    Recommend the right model tier (haiku/sonnet/opus) for a task based on complexity signals.

  • search_context

    Keyword search across all indexed symbols. Returns top 10 matches. Pass 'since' (e.g. 'HEAD~5', 'main', SHA) to restrict to recently-changed symbols.

  • smart_read

    Return only the relevant slice of a file based on a task description. Pass 'since' to filter to symbols modified after a git ref.

  • test_coverage

    Return test references for a symbol. Requires `booster index --tests` to populate the test index.

Public scan report

scanner v0.1.9 · 2026-09-26 · 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 qualitylocal package, no credentials required12/15
  • Maintenancelast push 77 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Booster compares

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

Safety score
88/100
higher than 80% 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
2
more than 65% of 2,711 AI and agents servers
Downloads a week
128
more than 68% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read

Install Agent Booster in Claude Code, Cursor or VS Code

claude mcp add agent-booster -- uvx agent-booster
Add to Cursor

What the publisher says

From the Agent Booster repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.sseshachala/agent-booster -->

Agent Booster

Cut AI coding agent token costs 5–15x by routing only the code that matters.

Instead of sending full source files to the model on every read, Agent Booster builds a symbol index of your codebase and returns only the functions and classes relevant to the current task.

How it works

Without Booster                    With Booster
─────────────────                  ────────────────────────────
Read executor.py                   smart_read executor.py + task
→ 1,881 lines (~6k tokens)         → 3 matching functions (~200 tokens)

Five layers work together:

Installation

Requires Python 3.10+.

pip install agent-booster          # symbol index + MCP tools
pip install agent-booster[embed]   # + semantic vector search (recommended)

Quickstart

Step 1 — Wire up your AI tool

booster init claude     # Claude Code
booster init cursor     # Cursor
booster init windsurf   # Windsurf
booster init codex      # OpenAI Codex CLI
booster init all        # all four

Each command shows exactly what files will change, asks for confirmation, then writes them. Fully reversible:

booster remove claude   # or cursor, windsurf, codex, all

Example — wiring up OpenAI Codex (booster init codex → booster start → booster gain):

Run once per project, not once per session.

The hooks live in .claude/settings.json and .mcp.json at the project root.

Every Claude Code session opened in this directory — any terminal window, same machine — picks them up automatically.

No per-session setup needed.

Step 2 — Index your codebase

Run once from your project root. Re-run after large refactors.

booster index && booster embed
# Indexed 260 files, 1800 symbols.
# Built embeddings for 1800 symbols.

The index is stored at .booster/ (gitignored). The index is shared across all sessions.

Step 3 — Restart your AI tool

The agent-booster MCP server is now available in every session. Claude Code (and other tools) will use smartread and searchcontext automatically on indexed files.

Step 4 — Track savings

booster gain

CLI reference

booster init

Writes the MCP server config and rules file for the target platform. Asks for confirmation before making any changes.

booster init claude     # .mcp.json + CLAUDE.md + .claude/settings.json hook
booster init cursor     # .cursor/mcp.json + .cursorrules
booster init windsurf   # ~/.windsurf/mcp.json + .windsurfrules
booster init codex      # ~/.codex/config.json + AGENTS.md
booster init all        # all four

booster init claude --yes   # skip confirmation (CI/scripts)

booster remove

Cleanly undoes everything init wrote. No residue.

booster remove claude
booster remove cursor
booster remove windsurf
booster remove codex
booster remove all

booster index

Shortened. The full README is on GitHub.

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

Agent Booster: common questions

Is Agent Booster MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Agent Booster safety report
How do I install Agent Booster?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Booster need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent Booster maintained?
The last commit was 116 days ago (2026-07-11). The latest release is v0.6.4.
What can I use instead of Agent Booster?
Servers from other publishers that do the same job: llmtrim MCP server, Basic Memory MCP server and Commonly MCP server.
How does Agent Booster compare with other AI and agents MCP servers?
safety score 88/100 (higher than 80% 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 Agent Booster

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

  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Commonly
    Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
    A
  • mcptoon
    MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).
    A
  • Agent Lsp
    Orchestrates language servers into 65 code-intelligence tools across 32 languages, token-optimized.
    A