Context ProviderCAUTION
A static MCP server that provides AI models with persistent tool context, preventing context loss between chats.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Status: beta — feature-complete, API stabilizing. See CHANGELOG.md for the latest release.
https://github.com/user-attachments/assets/d9c6c325-00f1-44d9-a805-b1d6588c0acf
Persistent context and learned instincts for Claude Desktop and Claude Code — surviving across sessions.
A TypeScript MCP server that gives Claude persistent Contexts (static tool rules) and Instincts (learned, confidence-scored rules distilled from sessions). No more re-establishing context in every new chat.
Architecture
Two core concepts:
Four subsystems:
- Engine — loads, matches, and merges contexts + instincts into injection payloads
- MCP Server (
src/server/index.ts) — stdio + HTTP transport, 10 MCP tools - CLI (
mcp-cp) — approval registry for instinct lifecycle management - Memory Bridge — optional sync of instincts to mcp-memory-service
Quick Start
git clone https://codeberg.org/doobidoo/MCP-Context-Provider.git cd MCP-Context-Provider npm install npm run build
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"context-provider": {
"command": "node",
"args": ["/path/to/mcp-context-provider/dist/server/index.js"],
"env": {
"CONTEXTS_PATH": "/path/to/mcp-context-provider/contexts",
"INSTINCTS_PATH": "/path/to/mcp-context-provider/instincts"
}
}
}
}Claude Code (global)
Add to ~/.mcp.json:
{
"mcpServers": {
"context-provider": {
"command": "node",
"args": ["/path/to/mcp-context-provider9b8936806e10OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-context-provider -- npx -y [email protected]
{
"mcpServers": {
"mcp-context-provider": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (10)
8 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
apply_auto_corrections | write | Apply auto-correction patterns from matching contexts to text |
approve_instinct | read | Approve an instinct for active use (sets approved_by to human) |
build_injection | read | Build a complete injection payload (contexts + instincts) for a tool/input combination |
get_syntax_rules | read | Get syntax-specific rules for a tool category |
get_tool_context | read | Get complete context (rules, syntax, preferences) for a specific tool |
list_available_contexts | read | List all loaded context categories and their descriptions |
record_outcome | read | Record a positive, negative, or neutral outcome for an instinct |
reject_instinct | read | Reject/deactivate an instinct and lower its confidence |
store_instinct | read | Store a new instinct candidate. Created as inactive with auto approval — use approve_instinct for human approval. |
sync_instincts | write | Push all local YAML instincts to mcp-memory-service. Requires memory bridge to be configured and connected. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (12)
mcp-context-provider-1.7.0.dxt
baseUrl: 'http://127.0.0.1:8000/api',
.gitleaks.toml
.pre-commit-config.yaml
.woodpecker.yml
docs/CHANGELOG.md
const instinctsDir = resolve(dirname(fileURLToPath(import.meta.url)), '../../instincts');
"MEMORY_BRIDGE_URL": "http://127.0.0.1:8000/api",
@modelcontextprotocol/sdk, yaml, zod, @types/node, typescript, vitest
assets/MCP-CONTEXT-PROVIDER.png
curl -sSL https://codeberg.org/doobidoo/MCP-Context-Provider/raw/branch/main/install.sh | bash
curl -sSL https://codeberg.org/doobidoo/MCP-Context-Provider/raw/branch/main/install.sh | bash
Gates applied: no_behavioural_pass.
9b8936806e10full audit observations/trust-audit/mcp-server/doobidoo__context-provider-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 9b8936806e10 | CAUTION | B | 89 | first audit |
Questions
What is the Context Provider MCP server?
A static MCP server that provides AI models with persistent tool context, preventing context loss between chats.
What tools does Context Provider expose?
10 in total: 8 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Context Provider safe to connect to an agent?
With care. The audit graded it B (89/100) and found 12 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Context Provider need?
No credential environment variables were found in its source, so it appears to need none.
How does Context Provider run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as mcp-context-provider at 2.0.0-beta.3.
How current is this page?
The grade is for one exact copy of the source (9b8936806e10), read on 2026-10-08. The repository is watched and re-audited when it changes.