
Context Vault
Hosted memory for AI agents: save what your agent learns and recall it in the next session.
- tools
- 11
- transport
- HTTP
- last updated
- Nov 12, 2026
Tools
11 toolsPublic tool metadata for what this MCP can expose to an agent.
save_contextSave an entry, or update one by id
Save an entry, or update one by id
No parameter schema in public metadata yet.
get_contextSearch the vault (full-text and semantic)
Search the vault (full-text and semantic)
No parameter schema in public metadata yet.
recallLight hints from a raw signal: a prompt, an error, a file path
Light hints from a raw signal: a prompt, an error, a file path
No parameter schema in public metadata yet.
list_contextBrowse entries by kind, tags or date
Browse entries by kind, tags or date
No parameter schema in public metadata yet.
delete_contextRemove an entry by id
Remove an entry by id
No parameter schema in public metadata yet.
ingest_urlFetch a page and save its readable text
Fetch a page and save its readable text
No parameter schema in public metadata yet.
ingest_projectScan a local project and register it
Scan a local project and register it
No parameter schema in public metadata yet.
create_snapshotCompile entries on a topic into one brief
Compile entries on a topic into one brief
No parameter schema in public metadata yet.
session_endSave a session summary and its discoveries
Save a session summary and its discoveries
No parameter schema in public metadata yet.
context_statusVault health: paths, counts, issues
Vault health: paths, counts, issues
No parameter schema in public metadata yet.
list_bucketsList buckets (a `bucket:<name>` tag scopes entries)
List buckets (a `bucket:<name>` tag scopes entries)
No parameter schema in public metadata yet.
Sponsors
Readme
context-vault
Persistent memory for AI agents: your agent saves what it learns and finds it again in the next session. Entries are plain markdown files on your machine.
Hosted tier: cloud sync, web dashboard, team sharing at app.context-vault.com
Vault Brain — 3D knowledge graph visualization showing nodes, edges, and hub detection
Quick start: a memory recalled in a new session, in under 5 minutes
Timed on a clean macOS account with Claude Code: about one minute of commands, plus your typing.
1. Install the binary (macOS and Linux; no Node needed):
curl -fsSL https://context-vault.com/install.sh | bash
It puts context-vault in ~/.local/bin. If it says that folder is not on your PATH, run the line it prints, then open a new terminal.
2. Connect your AI tools:
context-vault setup
Details
- Repository
- github.com/fellanh/context-vault
- Website
- context-vault.com
- Category
- AI & LLM Tools
- Transport
- HTTP
- Registry
- MCP registry, active