Take My Repo
Server Details
Find open repos and models, read reviews from people who ran them, get an install plan.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
Each tool targets a distinct object type: people/orgs (find_people), artifacts (search), a single artifact's facts (get_resource), its reviews (get_reviews), and install steps (get_install_plan). The only mild overlap is find_people vs search, since both are query-driven discovery, but the entity-type split (people vs repos/models/datasets) is spelled out clearly enough to prevent misselection.
Four of five names follow a clean verb_noun pattern (find_people, get_install_plan, get_resource, get_reviews). 'search' is a bare verb with no noun, a minor deviation in an otherwise predictable scheme.
Five tools cover the discovery-to-install-to-evaluation loop without redundancy; each has a clear job. This is a well-scoped surface for a repo/model discovery server.
The read path is solid (search, inspect, reviews, install), but get_reviews has no counterpart for writing a review or rating, even though the platform clearly hosts user reviews and ratings. find_people also returns a link to a person's page rather than their projects directly, leaving a small dead end for 'what has this person built?'.
Available Tools
5 toolsfind_peopleFind people and organizationsBRead-onlyInspect
People and organizations on GitHub (by name) and Hugging Face (by exact account name), with a link to their page on Take My Repo listing their public projects or models.
Inputs: query (required).
get_install_planGet the steps to install a projectARead-onlyInspect
The steps and rules for installing or running a project or model on the person's machine. When the person asked you to install it and you can run commands on their computer, follow them yourself right away: say in a few lines what is coming and what their app will ask them, then do it. Do not hand the steps back as a plan to approve. This tool itself installs nothing and never reports that an install succeeded.
Inputs: uid (required), os, gpu, agent, +1 more.
get_resourceGet one project or modelBRead-onlyInspect
Facts about one repository, model, demo or dataset: description, license (or that none is declared), topics, popularity, last update, source link, and Take My Repo's review count and average rating.
Inputs: uid (required).
get_reviewsRead reviewsARead-onlyInspect
Reviews written on Take My Repo by people who ran the project or model: rating, the machine they ran it on, and what worked or did not. An empty list means nobody has reviewed it yet, not that it is bad.
Inputs: uid (required).
searchSearch projects, models and demosARead-onlyInspect
Search GitHub repositories and Hugging Face models, demos and datasets together, by what the person wants to do. Returns ranked results with license, popularity, last update, where each value was read, and whether the maintainer declared support for the given operating system. 'fit' is 'declared' or 'unknown'; it is never a guess.
Inputs: query (required), os, kind.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Find open models and get download links with the SHA-256 each file must have.
Finds real, maintained open-source repos that fit your project. MCP grounding for coding agents.
Find the repo to build from: search 100k+ repos by base-fitness, clone free or buy over x402.
Search and install ready-made setups (rules, skills, MCP configs) for AI coding agents.
Related MCP Servers
- AlicenseAqualityBmaintenanceTell your AI agent what you want a model to do. It searches Hugging Face for each part of the job and tells you which parts already exist there: which are an exact fit, which to fine-tune, which to train, and which are just code. Every model it names is real, current, and sized for your hardware.3370 npm1MIT
- AlicenseAqualityBmaintenanceEnables users to scan Hugging Face for Apple-MLX models, estimate memory fit and decode speed for their Mac, and get ranked recommendations for a use case, with all agent work running locally.112MIT
- AlicenseNot gradedqualityBmaintenanceSearch, rank, and compare 500K+ AI models from 13+ platforms with VRAM and license constraints1MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to pull measured local-LLM benchmark data and hardware-aware model picks — ranked configs with decode tok/s, quant and backend details, hardware catalogues, and repo submissions for review. Answers questions like "what should I run on a Strix Halo for coding?" with sourced numbers rather than invented ones.91 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.