Connection check
local install
hydramcp
Connect agents to agents. MCP server for querying any LLM through your existing subscriptions: compare, vote, and synthesize across GPT, Gemini, Claude, and local models from one terminal.
Tools
8
GitHub stars
15
Installs / wk
15
Licence
MIT
Transport
stdio
Last checked
never
Tools & capabilities
8 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
analyze_file
from source
Offload file analysis to a worker model. The file is read server-side — it never enters your context window. You send a file path and a question, and get back only the analysis.… Offload file analysis to a worker model. The file is read server-side — it never enters your context window. You send a file path and a question, and get back only the analysis. OUTPUT: Markdown with the model
ask_model
from source
Query any AI model with a prompt. Returns the model Query any AI model with a prompt. Returns the model
compare_models
from source
Query 2-5 models in parallel with the same prompt. Returns side-by-side comparison with latency and token metrics. Query 2-5 models in parallel with the same prompt. Returns side-by-side comparison with latency and token metrics.
consensus
from source
Query 3-7 models and aggregate responses using voting strategy (majority/supermajority/unanimous). Returns consensus answer with confidence score. Query 3-7 models and aggregate responses using voting strategy (majority/supermajority/unanimous). Returns consensus answer with confidence score.
list_models
from source
List all available models across all providers. Run this first to see what you can query. List all available models across all providers. Run this first to see what you can query.
session_recap
from source
Read previous Claude Code sessions from disk and generate a smart-sized recap using a large-context model. Claude never sees the raw session data — only the distilled summary. O… Read previous Claude Code sessions from disk and generate a smart-sized recap using a large-context model. Claude never sees the raw session data — only the distilled summary. OUTPUT: Returns markdown starting with
smart_read
from source
Surgical code extraction from files. Returns ONLY relevant code sections with line numbers — not analysis. OUTPUT: Markdown with extracted code sections (verbatim, with line num… Surgical code extraction from files. Returns ONLY relevant code sections with line numbers — not analysis. OUTPUT: Markdown with extracted code sections (verbatim, with line numbers), minimal annotations, file metadata, latency, token usage. Shows
synthesize
from source