context-doctor
NPM · CONTEXT-DOCTOR
Cut LLM agent token use in Claude Code, Cursor, Codex, Gemini CLI. Local, no API key. gAI Ventures.
Available components
Last scanned (2 hours ago)
Scores higher than 98% of npm servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to KushalP1/context-doctor). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability77
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 869 tokens (~124/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 74% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 4 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.42.0 → 0.43.0 functional
- 3 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- Package version: 0.41.0 → 0.42.0 functional
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.40.0 → 0.41.0 functional
- 30 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- Package version: 0.39.0 → 0.40.0 functional
- 29 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.38.0 → 0.39.0 functional
- 28 Oct 26 +27
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Stability: 0.97 → pass security
- Dependency health: unverified → pass ▲ functional
- 27 Oct 26 0
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Tool coverage: 81% → 74% ▼ functional
- Schema quality: 153 → 124 ▲ functional
- Dependency health: unverified → pass ▲ functional
- Package version: 0.37.0 → 0.38.0 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/context-doctor@0.43.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | KushalP1/context-doctor |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/KushalP1/context-doctor/.github/workflows/publish.yml@refs/tags/v0.43.0 |
| Rekor log index | 3686785993 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:a97d05d4cd0d28d36bf2a4d1e96109c3b53f47fa6abb49b9b9dd2d1699c9d2538bfab2aa7f63a5f0d2c4c9693e0712320ab9a80db5a684ce98bf98c41 |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
context_best_practices ~35
Checklist for keeping context lean and prompts cacheable, optionally per provider.
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | – | Default: general |
No output schema declared.
No examples provided.
optimize_context ~129
Rewrite a conversation to reclaim tokens (dedupe, trim stale tool results, strip base64; prune-history is lossy). Returns slimmed JSON and the savings. Use after profile_context finds waste the user wants fixed; prune-history only with the user's consent, then write the summary the result asks for.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation | string | yes | Conversation JSON |
| keep_recent | integer | – | Tail messages kept (default 6) |
| max_tool_result_tokens | integer | – | Per trimmed result (default 300) |
| strategies | array | – | Default: dedupe, trim-tool-results, strip-base64 |
No output schema declared.
No examples provided.
pack_context ~181
Read only the parts of large files a question needs: the chunks that best match `query` within `max_tokens`, with ids and line ranges. No query: an outline; pick with `ids`. Use instead of reading a big doc, log or folder whole when not editing it. Text, code, PDF, Word, PowerPoint, ODT.
| Name | Type | Req | Description |
|---|---|---|---|
| ids | array | – | Chunk ids, e.g. docs/guide.md#4 |
| max_tokens | integer | – | Budget, default 4000 |
| model | string | – | Model to count for |
| paths | array | – | Files or folders, absolute paths |
| query | string | – | The question; omit for an outline |
| semantic | boolean | – | Also rank by meaning (local Ollama embeddings) |
| text | string | – | Raw text to pack instead of files |
No output schema declared.
No examples provided.
profile_context ~146
Profile a conversation's context: token breakdown, largest blocks, wasted context. Pass `conversation` (JSON or text) or, in a chat app, a `sketch` (~120 tokens). Call it when the user asks about tokens, cost, speed or limits, and once past ~30 turns or 3+ large pastes. Act on the top finding.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation | string | – | JSON or text; in a chat app pass `sketch` |
| model | string | – | e.g. claude-sonnet-5 |
| sketch | object | – | For chat apps. One size hint per block: lines for code, words for prose, chars for logs. |
No output schema declared.
No examples provided.
recall ~56
Search this session's transcript on disk (compacted turns, cleared tool output) for `query`: best excerpts with time and position. Use before asking the user again.
| Name | Type | Req | Description |
|---|---|---|---|
| max_tokens | number | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
save_handoff ~125
Save a handoff for continuing in a new chat (a chat's history cannot be cut; a new chat can). Write `brief` yourself (≤400 tokens: goal, decisions, state, open items, identifiers); put what must stay exact in `verbatim`. Only when the user agrees.
| Name | Type | Req | Description |
|---|---|---|---|
| brief | string | yes | – |
| chat_tokens | number | – | Chat size, from profile_context |
| model | string | – | – |
| title | string | – | – |
| turns | number | – | – |
| verbatim | array | – | Code, config, figures |
No output schema declared.
No examples provided.
How do I install the context-doctor MCP server?
context-doctor runs locally as an npm package, launched with npx -y context-doctor. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · context-doctor
claude mcp add kushalp1-context-doctor -- npx -y context-doctor
What is the context-doctor MCP server?
context-doctor is an MCP server listed in the public MCP registry as io.github.KushalP1/context-doctor. Cut LLM agent token use in Claude Code, Cursor, Codex, Gemini CLI. Local, no API key. gAI Ventures. This page covers its npm package (context-doctor).
Is the context-doctor MCP server safe to use?
context-doctor scores 95 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the context-doctor MCP server expose?
context-doctor exposes 6 tools: profile_context, optimize_context, pack_context, save_handoff, recall, context_best_practices. Their descriptions and schemas cost roughly 672 tokens of context every time the server is loaded.
Is the context-doctor MCP server still maintained?
context-doctor is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the context-doctor MCP server under?
context-doctor declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.