Skip to main content
Glama
SuperMarioYL

ctxfeed

by SuperMarioYL
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GLM_API_KEYNoAPI key for GLM (alternative to ZHIPU_API_KEY).
CTXFEED_MODELNoModel to use, either glm or deepseek. Overridden by --model.
ZHIPU_API_KEYNoAPI key for GLM (Zhipu).
DEEPSEEK_API_KEYNoAPI key for DeepSeek.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
query_repoA

Answer question using the whole repo's files in-context.

Ingests the repo's ingestible files into the selected model's context window (cache-aware ShardPlan ordering; GLM-5.2 1M by default, DeepSeek V4 128k via model="deepseek") and asks the question in a single model round-trip. Returns the answer prefixed with a one-line context summary (files + tokens). Transient API errors (429/5xx) are retried with backoff; a terminal failure returns a structured error (v0.2).

Args: question: the repo-wide question (e.g. "where is the auth middleware handled?"). repo: optional repo root override (defaults to the --repo arg or CTXFEED_REPO_ROOT env var). model: optional model override ("glm" | "deepseek"; defaults to the server's --model / CTXFEED_MODEL).

list_filesB

List the ingestible files ctxfeed would serve in-context.

One line per file: path · tokens · layer · cached?. Useful for an agent to see what's about to be served before querying.

cost_deltaC

Per-query token cost vs Claude Opus at equal repo size.

The m3 "star-able" number: GLM-5.2 + DeepSeek V4 vs Opus, plus files-accepted vs ChatGPT's 40-file cap. Read-only (v0.2): does not mutate the cache store.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 3 tools

Disambiguation5/5

query_repo, list_files, and cost_delta each perform a clearly distinct action: answering a question, inventorying served files, and reporting cost metrics. There is no overlap, so an agent can easily select the right tool.

Naming Consistency4/5

All names use snake_case consistently and are readable. However, query_repo and list_files follow a verb_noun pattern while cost_delta is a noun phrase, which is a minor deviation from a fully predictable convention.

Tool Count4/5

Three tools is a tight but reasonable scope for a read-only repo-context server. Each tool has a distinct role, though cost_delta is more auxiliary than the core query/list functions, making the set feel slightly minimal rather than perfectly balanced.

Completeness4/5

The surface covers listing ingestible files, querying the whole repo in-context, and comparing per-query cost. Gaps exist for targeted file queries, filtering, or partial-repo selection, but the whole-repo query and file listing let agents work around these limitations.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources