Context MCP Server

Project memory for Claude: decisions, pipelines, and constraints across conversations.

Local serverstdioPython

What is the Context MCP server?

Most knowledge and memory work still happens through a UI a human drives. Context MCP server moves it into the conversation instead. Project memory for Claude: decisions, pipelines, and constraints across conversations.

The short version

Project memory for Claude. Records design decisions, pipeline flows, and constraints so Claude maintains context across conversations.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • Abstention — measures whether get_context says "nothing relevant" instead of confabulating on no-answer queries; the 0.20 relevance floor is the highest with zero
  • Over — budget summaries are now floored and reported.** Truncating the
  • record_entry — Unified write tool — record a decision, pipeline, or constraint via kind, with per-kind fields validated server-side. Consolidates the former
  • get_context — Retrieve relevant entries by query, tags, scope, or ID — relevance-ranked, pulls related_to links by default
  • query_entriesExact structured-field filtering (status, origin, tags, scope, hardness, supersession, dates) — deterministic, no ranking; distinct from
  • get_project_summary — Compact overview for conversation start
  • update_entry — Update any entry by ID
  • deprecate_entry — Retire an entry with reason (optional merge_into folds a duplicate into a survivor)
  • prune_stale — Find entries not verified recently
  • get_compaction_report — Check if last compaction lost any context
  • verify_quality — Scan entries for thin rationale, missing tags, isolated arcs (auto-called by PreCompact hook)
  • export_markdown — Regenerate DECISIONS.md from the decisions store — a derived, read-only projection

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Context.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Context's toolset — Abstention, Over, record_entry and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jarmstrong158; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Context's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
Abstentionmeasures whether get_context says "nothing relevant" instead of confabulating on no-answer queries; the 0.20 relevance floor is the highest with zero false-abstention on the eval set ([evals/abstention.py](evals/abstenti
Overbudget summaries are now floored and reported.** Truncating the
record_entryUnified write tool — record a decision, pipeline, or constraint via kind, with per-kind fields validated server-side. Consolidates the former record_decision/record_pipeline/record_constraint (still dispatchable by those
get_contextRetrieve relevant entries by query, tags, scope, or ID — relevance-ranked, pulls related_to links by default
query_entries**Exact structured-field filtering** (status, origin, tags, scope, hardness, supersession, dates) — deterministic, no ranking; distinct from get_context's relevance search
get_project_summaryCompact overview for conversation start
update_entryUpdate any entry by ID
deprecate_entryRetire an entry with reason (optional merge_into folds a duplicate into a survivor)
prune_staleFind entries not verified recently
get_compaction_reportCheck if last compaction lost any context
verify_qualityScan entries for thin rationale, missing tags, isolated arcs (auto-called by PreCompact hook)
export_markdownRegenerate DECISIONS.md from the decisions store — a derived, read-only projection
reload_constraintsRe-surface the constraints-only block on demand mid-session (rules refresh, not the full store)
export_snapshotWrite the whole store to a committable .context-keeper/memory.json.gz for sharing project memory via git

Example prompts to try

  • Use Context to Abstention.
  • Use Context to Over.
  • Use Context to record entry.

Frequently asked questions

It connects Context to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Abstention, Over, record_entry, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Context directly.