CtxNest is a local-first, centralized context engine providing AI agents with 42 tools to manage versioned markdown knowledge across projects and a personal knowledge base, optimized for context window economy.
File Reading
read_file / read_files / read_file_by_path — Read single, batch (up to 200), or path-based files
read_file_outline — Headings-only outline without loading full content
read_section / read_file_lines — Read a single heading's body or a specific line range
describe_file — File metadata (tags, size, history, backlinks) without loading content
File Writing
create_file / create_files — Create single or batch (up to 200) files
update_file / update_file_section — Full replace or surgical per-heading update (auto-commits to git)
delete_file / delete_files — Delete single or batch (up to 500) files
move_file — Rename or relocate a file
journal_append — Append a timestamped entry to today's journal
Search & Discovery
search — FTS5 full-text search with inline excerpts and highlights
bundle_search — Search and concatenate results into a token-budgeted XML/Markdown blob
regex_search / grep_in_file — Cross-file or within-file regex search
find_related — Files sharing tags, ranked by overlap
whats_new — Files created/modified since a checkpoint
project_map — Compact indented outline of an entire project or knowledge base
Tagging & Favorites
add_tags / remove_tags / list_tags — Manage tags
set_favorite — Mark/unmark favorites
suggest_tags — Propose tags based on corpus (no LLM required)
tag_search_results — Bulk-apply tags to all files matching a query
Folders & Projects
list_files / list_folders — List files or folders with filters
create_folder / delete_folder — Create (nested) or recursively delete folders
register_project / list_projects — Register external repos and list all projects
stats — Aggregate counts, top tags, per-project breakdown
Versioning & Integrity
get_history / get_diff / restore_file — Git history, diffs, and rollback
commit_backup — Commit and push a project to git
diff_against_disk / refresh_index — Detect and reconcile drift from external edits
Web Clipping
clip_url — Fetch a page, extract content via Readability, and store as Markdown (supports auth-walled pages with cookie/token retry)
All file-returning tools include est_tokens and size_bytes; list/search tools inline tags and excerpts to minimize round-trips.
This is a simple "Hello World" MCP (Model Context Protocol) server created for testing purposes.
This server exposes the following tools:
hello-world: A greeting tool.
Input: name (string)
Output: A personalized hello message.
stat: A status check tool.
Output: Returns "running well".
Related MCP server: brain-mcp
Node.js (v18 or higher)
npm
Clone or navigate to the project directory.
Install dependencies:
npm installTo start the server on stdio:
npm startTo compile the TypeScript source code:
npm run buildThis is only a test project.
A simple hello world tool
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The name to say hello to |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only says 'simple hello world tool' without disclosing traits like output format, side effects, or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence) and has no waste, but it is under-specified. It could be expanded slightly to improve clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 required param, no output schema), the description is minimally adequate. However, it lacks detail about the return value or what the tool actually does with the name.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (the 'name' parameter has a description). The description adds no additional meaning beyond the schema's 'The name to say hello to'. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description says 'A simple hello world tool', which implies a greeting but does not explicitly state the verb (e.g., 'Says hello') or the resource. It is somewhat vague but not a tautology.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs. the sibling 'stat'. There is no mention of context or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check the status of the server
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are available, so the description bears full responsibility for behavioral disclosure. It merely states 'Check the status' without detailing what status information is returned (e.g., health, uptime) or any potential side effects. The description lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence without unnecessary words. It is highly concise and front-loaded with the action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is too minimal. It does not explain what the output looks like or potential error conditions. For a simple status tool, it is adequate but could be improved by briefly noting output format (e.g., plain text, JSON).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so no parameter information is needed. The description adds no meaning beyond the input schema, but per guidelines, 0 parameters yields a baseline of 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Check the status of the server' clearly identifies the verb (check) and resource (status of the server). It is specific and distinct from the sibling tool 'hello-world', though it does not explicitly differentiate from it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusion criteria. It only states the action without context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v9.5.3add_tagsbundle_searchclip_urlcommit_backupconfirm_handcreate_filecreate_filescreate_folderdelete_filedelete_filesdelete_folderdescribe_filedescribe_hands_schemadiff_against_diskfind_relatedget_diffget_historygrep_in_filehello-worldjournal_appendlist_fileslist_folderslist_handslist_projectslist_tagsmove_fileonboard_agentproject_mapread_fileread_file_by_pathread_file_linesread_file_outlineread_filesread_sectionrefresh_indexregex_searchregister_projectreload_handsremove_tagsrestore_filesearchset_favoritestatstatssuggest_tagstag_search_resultsupdate_fileupdate_file_sectionwhats_newv9.4.0onboard_agent3 fields changedInput schema / properties / confirmAdded value: +{
+ "description": "MANDATORY: Set to true only after obtaining explicit user consent to modify context files.",
+ "type": "boolean"
+}Input schema / properties / target_agent / enumPrevious value: -[
- "claude-code",
- "codex",
- "gemini",
- "cursor",
- "continue",
- "generic"
-]New value: +[
+ "claude-code",
+ "codex",
+ "gemini",
+ "antigravity",
+ "cursor",
+ "continue",
+ "generic"
+]Input schema / requiredPrevious value: -[
- "project_id"
-]New value: +[
+ "project_id",
+ "confirm"
+]v9.1.2onboard_agentScored across 2 tools
The two tools, hello-world and stat, have completely distinct purposes with no overlap. An agent can easily distinguish between them without confusion.
The naming conventions are not consistent: hello-world uses a hyphen and two words, while stat is a single word. This inconsistency could confuse an agent expecting a uniform pattern.
With only 2 tools, the server feels very thin. For a server named ctxtest, more tools would be expected to provide meaningful functionality beyond a hello world and status check.
The tool surface is too sparse to infer a clear domain. There are obvious gaps: no tools for configuration, error handling, or any context-related operations that the server name might imply.
Your versioned memory across every AI tool — context maps, personal memory, and tasks over MCP.
One shared context your team's AI tools read & write over MCP. No re-explaining. Free.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
AI research library. Save, organise and reuse notes and webpages as clean markdown context.
