Context Engine
NPM · @SHAM-SUNDAR-SENTHIL-KUMAR/MCP-SERVER
Local-first persistent context memory MCP server for AI coding agents.
Available components
Last scanned (3 hours ago)
Scores higher than 30% of npm servers
Category Memory and Knowledge
Recent critical change
CVE-2026-41242 affects this package (22 Oct 2026). See the changelog before you install this server.
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 Security80
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 0.6.1, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 53 of 137 dependencies flagged as unhealthy (2 deprecated). View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 15 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability70
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 659 tokens (~73/item across 9 items; 9 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "merge" implies "merge" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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 +56
- CVE-2026-114113 affects this package: high ▼ security
- CVE-2026-44294 affects this package: high ▼ security
- CVE-2026-44289 affects this package: high ▼ security
- CVE-2026-44292 affects this package: high ▼ security
- CVE-2026-44288 affects this package: high ▼ security
- CVE-2026-114111 affects this package: high ▼ security
- CVE-2026-45740 affects this package: high ▼ security
- CVE-2025-66414 affects this package: high ▼ security
- CVE-2026-44291 affects this package: high ▼ security
- CVE-2026-54269 affects this package: high ▼ security
- CVE-2026-44293 affects this package: high ▼ security
- CVE-2026-111769 affects this package: high ▼ security
- CVE-2023-54404 affects this package: high ▼ security
- CVE-2026-48712 affects this package: high ▼ security
- CVE-2026-44290 affects this package: high ▼ security
- CVE-2026-114112 affects this package: high ▼ security
- CVE-2026-41242 no longer affects this package ▲ security
- Known CVEs: CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 0.6.1, a direct dependency. A fixed version is available. security
- Score status: failed → scored ▲ functional
- 22 Oct 26 −36
- CVE-2026-41242 affects this package: high ▼ critical
- Known CVEs: unverified → fail ▼ critical
- Score status: scored → failed ▼ critical
- CVE-2026-111769 no longer affects this package ▲ security
- CVE-2025-66414 no longer affects this package ▲ security
- Malware scan: unverified → pass ▲ security
- Dependency health: unverified → 0.81 ▲ functional
- 21 Oct 26 +20
- Known CVEs: fail → unverified ▼ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- MCP protocol: unverified → fail ▼ functional
- Dependency health: partial → unverified ▼ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: 0 functional
- First check of Schema quality: pass functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- Package version: 0.1.2 → 0.1.4 functional
- 20 Oct 26 16
First indexed and scored.
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/@sham-sundar-senthil-kumar/mcp-server@0.1.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 16 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-6prh-2h8m-c8cw | CVE-2026-111769 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:L/A:N | yes |
| GHSA-w48q-cv73-mx4w | CVE-2025-66414 | high | yes | |
| GHSA-2pr8-phx7-x9h3 | CVE-2026-44294 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-66ff-xgx4-vchm | CVE-2026-44293 | high | yes | |
| GHSA-685m-2w69-288q | CVE-2026-44289 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-75px-5xx7-5xc7 | CVE-2026-44291 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-f38q-mgvj-vph7 | CVE-2026-54269 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-fx83-v9x8-x52w | CVE-2026-44292 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-jggg-4jg4-v7c6 | CVE-2026-45740 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-jvwf-75h9-cwgg | CVE-2026-44290 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-q6x5-8v7m-xcrf | CVE-2026-44288 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-wcpc-wj8m-hjx6 | CVE-2026-48712 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-f88m-g3jw-g9cj | CVE-2026-114113 | high | yes | |
| GHSA-rgj7-g3m4-5g8c | CVE-2026-114112 | high | yes | |
| GHSA-wq5f-xc86-pv6w | CVE-2026-114111 | high | yes | |
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 137 packages
| Packages resolved | 137 |
|---|---|
| Deprecated | 2 |
| Stale | 50 |
| No linked repository | 1 |
| 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 →
branch ~79
Create a new branch or switch to an existing branch by name. If the branch already exists, it switches to it cleanly without modifying history.
| Name | Type | Req | Description |
|---|---|---|---|
| from_commit | string | – | Optional starting commit ID for new branches only |
| name | string | yes | Name of the branch to create or switch to |
| session_id | string | – | Optional session ID |
No output schema declared.
No examples provided.
checkout ~41
Roll back context memory to a previous commit ID
| Name | Type | Req | Description |
|---|---|---|---|
| commit_id | string | yes | Target commit ID to checkout |
| session_id | string | – | Optional session ID |
No output schema declared.
No examples provided.
commit ~74
Record key architectural decision, bug fix, or findings into context graph
| Name | Type | Req | Description |
|---|---|---|---|
| kept_refs | array | yes | Critical code snippets or facts to keep verbatim |
| session_id | string | – | Optional session ID |
| summary | string | yes | Plain language explanation of the decision or finding |
| topic | string | yes | Brief topic label |
No output schema declared.
No examples provided.
gather_context ~61
MANDATORY ON NEW CHAT OR CONTEXT RESET: Reconstructs and retrieves bounded context memory (rolling summary and all preserved architectural facts) from previous sessions.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | – | Optional session ID to gather context from. Defaults to active project session. |
No output schema declared.
No examples provided.
get_context_tree ~52
Outputs a highly structured, clean markdown visual text graph tree of all active branches, commits, and memory states straight to the chat view.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | – | Optional session ID to inspect memory tree for. |
No output schema declared.
No examples provided.
merge ~63
Merge a feature context branch into target branch (defaults to main)
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | – | Optional session ID |
| source_branch | string | yes | Source branch name to merge from |
| target_branch | string | – | Target branch name to merge into (defaults to main) |
No output schema declared.
No examples provided.
observe_turn ~94
Autonomous background observer: Records conversation turn history, runs dual-tier triage, and auto-commits compressed state every 5-10 turns.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | Turn message text to observe and buffer |
| role | string | – | Role of the message sender |
| session_id | string | – | Optional session ID |
| workspace_path | string | – | Optional workspace path to trigger auto-branching on directory shifts |
No output schema declared.
No examples provided.
override_memory_node ~138
Power user tool to target an exact node in the SQLite history graph and forcibly overwrite its text content, completely pruning out incorrect details or debug junk.
| Name | Type | Req | Description |
|---|---|---|---|
| commit_id | string | yes | The exact commit ID in the memory graph to overwrite |
| kept_chunks | array | – | Optional list of verified permanent facts to retain |
| new_summary | string | yes | New summary text replacing the original reason log |
| new_topic | string | – | Optional new topic title |
| prune_transient | boolean | – | If true, automatically deletes all transient logs and discarded chunks for this node (default: true) |
| session_id | string | – | Optional session ID |
No output schema declared.
No examples provided.
recall ~57
Recall previous commits and context facts for a given query
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Keyword or topic query to search context history |
| scope | string | – | Search active branch or all branches |
| session_id | string | – | Optional session ID |
No output schema declared.
No examples provided.
How do I install the Context Engine MCP server?
Context Engine runs locally as an npm package, launched with npx -y @sham-sundar-senthil-kumar/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @sham-sundar-senthil-kumar/mcp-server
claude mcp add shamsundarsk-mcp-server -- npx -y @sham-sundar-senthil-kumar/mcp-server
What is the Context Engine MCP server?
Context Engine is an MCP server listed in the public MCP registry as io.github.shamsundarsk/mcp-server. Local-first persistent context memory MCP server for AI coding agents. This page covers its npm package (@sham-sundar-senthil-kumar/mcp-server).
Is the Context Engine MCP server safe to use?
Context Engine scores 56 out of 100 on VerifyMCP. We recorded 16 known advisories against it as of 5 November 2026. It declares no install or post-install scripts. 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 Engine MCP server expose?
Context Engine exposes 9 tools: gather_context, get_context_tree, override_memory_node, observe_turn, recall, and 4 more. Their descriptions and schemas cost roughly 659 tokens of context every time the server is loaded.
Is the Context Engine MCP server still maintained?
Context Engine 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.