PrinceGabriel-lgtm/freshcontext-mcp

> **This package is no longer developed.** 0.5.3 is the last release of freshcontext-mcp.
> It and every earlier release stay available under the MIT License, as is; there will be no
> further feature releases. For FreshContext services, see .
> Security reports: see SECURITY.md.
I asked Claude to help me find a job. It gave me a list of openings. I applied to three of them. Two didn't exist anymore. One had been closed for two years.
Claude had no idea. It presented everything with the same confidence.
That's the problem freshcontext fixes.
This repository is the integrated FreshContext Core/MCP package.
**Category: context integrity infrastructure.** FreshContext sits between context acquisition and agent action. Its job is to decide whether information entering an AI workflow is still fresh, attributable and coherent enough for the system to rely on. Core is the reusable engine that scores, ranks, explains and turns candidate context into decision-ready context, with signed verdicts recorded in a verifiable ledger. MCP is the first live host interface over that engine — one interface over the methodology, not the product itself.
> **Live demo:** api.freshcontext.dev/demo — same model, same query, two completely different answers. Only the temporal layer changed.
>
> **Integrate it into an existing stack:** freshcontext.dev/integration — start with one bounded RAG, agent, retrieval, or governance workflow and objective acceptance criteria.
---
The problem
Large language models retrieve web data semantically. Cosine similarity finds the documents that match a query best — but cosine doesn't know when a document was written.
So a 2022 blog post and a 2026 paper can score nearly identically. The model gets a context window full of stale documents and faithfully summarizes 2022 advice for a 2026 question.
That's not hallucination. That's correct summarization of corrupted retrieval.
> **Most RAG pipelines rank context correctly semantically but incorrectly temporally.**
---
The layer
FreshContext is **context integrity infrastructure for AI agents and retrieval systems**. It sits between retrieval and reasoning:
FreshContext evaluates freshness, source profile, confidence, utility, provenance material, and failure honesty before context reaches the LLM. The temporal core uses Decay-Adjusted Relevancy:
- R_0 — base semantic relevancy (whatever your retriever already gives you)
- λ — source-specific decay constant (HN ≈14h half-life, blogs ≈29d, academic papers ≈1.6y)
- t — hours elapsed since publication
- R_t — decay-adjusted relevancy at query time
That's the core correction. No model swap. No re-embedding. No re-indexing. The layer drops onto whatever retrieval pipeline you already have.
**The layer is the product.** The named adapters shipped with this repo demonstrate compatibility across different source classes. The DAR engine, the freshness envelope, Source Profiles, and the FreshContext Specification are the moat.
---
The standard
Every FreshContext-compatible response wraps content in a structured envelope:
**When** it was retrieved. **Where** it came from. **How confident** we are the date is accurate.
The FreshContext Specification v1.2 is published as an open standard under MIT licence. Any tool, agent, or system that wraps retrieved data in this envelope is FreshContext-compatible. → Read the spec · Read the methodology
---
Architecture boundary
FreshContext Core is the reusable center of the current integrated package. It owns signal normalization, freshness scoring, Source Profiles, decision output, envelope formatting, failure guards, shared types, rank/explain primitives, and the context-conditioned utility primitive.
MCP is the primary reference/interface implementation over Core. Claude Desktop is supported, but not required. The MCP tool surface exposes named reference adapters and a live interface for using the system.
The production Cloudflare Worker now uses Core-backed envelope generation. Worker-specific concerns remain outside Core: MCP transport, runtime guards, KV cache policy, cache metadata injection, JSON parse/replace cache helpers, D1 feeds, cron, rate limiting, and Store/feed scoring/provenance.
See Architecture for the layer boundaries, the package surface, and what is not yet separated.
Core import path