mcp server
contextweaver
MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.
Description as published by the maintainer. Source
- version 0.15.0
- active
active — Most recent push to the repository was 2026-08-05.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 8 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-05 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 153 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 0.15.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-06-14 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | Apache-2.0 | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-06-14 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub |
Where to get it
Related, by what their authors tagged them
-
Bilinc
— last commit 2026-08-06, shares agent-infrastructure, context-management
Hosted agent memory with provenance, contradiction surfacing, and snapshot rollback.
-
ai.smithery/neverinfamous-memory-journal-mcp
— last commit 2026-07-22, shares context-management
A MCP server built for developers enabling Git based project management with project and personal…
-
frappucc1no-recall-loom-recallloom
— last commit 2026-08-06, shares context-management
Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updati…
-
ContextStream
— last commit 2026-08-05, shares context-management
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
-
A2CR
— last commit 2026-08-05, shares context-management
Save AI-agent handoff checkpoints, WorkStash notes, and WorkThreads in a local A2CR workspace.
-
Context Book
— last commit 2026-06-06, shares context-management
Stop re-explaining yourself to Agents. Give it the right context, right when needed.
-
io.github.buttonmonkey/mcp-loom
— last commit 2026-07-06, shares context-management
Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.
-
Sugar
— last commit 2026-07-20, shares context-management
Autonomous AI development system with persistent task queue and background execution
-
ContextStream MCP Server
— last commit 2026-08-05, shares context-management
ContextStream MCP server for code context, memory, search, and AI tools.
-
io.github.daedalus/mcp-smart-proxy
— last commit 2026-04-22, shares context-management
An MCP server that provides a smart proxy to other mcp servers
These share tags the maintainers applied themselves, such as agent-infrastructure, context-management. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
Also from dgenio
-
ChainWeaver
— last commit 2026-08-04
Expose deterministic ChainWeaver flows as MCP tools without LLM calls between steps.
How the author describes it
Topics the maintainer set on GitHub: agent-infrastructure, ai-agents, context-management, mcp, prompt-engineering, python, token-budgeting, tool-routing.
Bring your own setup
We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.
Join ZBS AI Practice Lab