A2A Governance Bridge MCP server. Tools: verify agent compliance, authorize a2a transaction, get trust registry. Built by MEOK AI Labs.
Free
Nothing to run from here
Kontexta is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
The local Brain and Hands for AI coding agents (MCP Server)
Quickstart
# 1 — run it from where its publisher ships it
npx -y kontexta-mcp
# 2 — the plan is chosen at checkout, in the browser
# 3 — ask your agent something
> The local Brain and Hands for AI coding agents (MCP Server)
Publishernot claimed
SAAll 2 servers
safiyu2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Kontexta as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add kontexta-mcp -- npx -y kontexta-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
This is a paid listing, so the CLI has to be signed in and the licence has to be on your account — how the login works. Until then the install stops with the price rather than half-writing a config entry.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
66 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Record a free-form decision/abandonment/observation note in the current project
Takes no parameters.
Example callreturns →
Record a topic/intent pivot. Use when the user redirects what you
Takes no parameters.
Example callreturns →
Run the distillation pipeline: read raw events since the high-water mark, group by topic, write mechanical markdown entries, advance high-water. Idempotent. Auto-provisions a project row for orphan slugs (e.g.
Takes no parameters.
Example callreturns →
Report the journal backlog and high-water mark for a project.
Takes no parameters.
Example callreturns →
After dispatching subagents to upgrade mechanical journal entries to LLM-narrative, call this with the affected task slugs. Updates journal_meta.status_latest to mark the entries as upgraded.
Takes no parameters.
Example callreturns →
Run journal retention/archival for a project. Idempotent. Prunes old raw .jsonl files and archives cold tasks per the configured retention policy.
Takes no parameters.
Example callreturns →
SIDE-EFFECTFUL. Create a new tracked entity \u2014 any named thing you schedule events against (a server, a delivery van, a store location, a piece of equipment, a room, etc.). Not idempotent: a duplicate name (case-insensitive) throws. Returns
Takes no parameters.
Example callreturns →
SIDE-EFFECTFUL. Patch an existing entity
Takes no parameters.
Example callreturns →
DESTRUCTIVE. Permanently delete an entity AND cascade-delete every event and link attached to it. Not idempotent \u2014 deleting an unknown id throws. Returns
Takes no parameters.
Example callreturns →
Read-only; no side effects, auth, or rate limits. List tracked entities, each annotated with its outgoing and incoming dependency links. Returns
Takes no parameters.
Example callreturns →
SIDE-EFFECTFUL. Create or update a directed dependency edge between two entities (e.g.
Takes no parameters.
Example callreturns →
SIDE-EFFECTFUL. Add a one-off time window (downtime, maintenance, a delivery, a shift, an inspection, etc.) to an entity. NOT idempotent \u2014 calling this twice creates two events.
Takes no parameters.
Example callreturns →
SIDE-EFFECTFUL. Patch an existing event (move it, retitle it, re-home it to a different entity, etc.). The merged result is re-validated \u2014 shrinking
Takes no parameters.
Example callreturns →
DESTRUCTIVE. Delete one event by id. Idempotent \u2014 deleting an already-absent id is a no-op. Returns
Takes no parameters.
Example callreturns →
Read-only; no side effects, auth, or rate limits. List events overlapping a window (half-open \u2014 an event ending exactly at
Takes no parameters.
Example callreturns →
Read-only; no side effects, auth, or rate limits. Report scheduling conflicts in a window: overlaps on the same entity (\
Takes no parameters.
Example callreturns →
Read-only; no side effects, auth, or rate limits. Export events in a window as an RFC 5545 ICS calendar (UTC times, no VTIMEZONE needed) for import into Outlook/Calendar apps. Returns
Takes no parameters.
Example callreturns →
Append a timestamped text entry to today
Takes no parameters.
Example callreturns →
Create a new markdown or mermaid file in the knowledge base or project. This operation writes a new file to disk and adds it to the local SQLite FTS5 index. Destination can be
Takes no parameters.
Example callreturns →
Read one file
Takes no parameters.
Example callreturns →
Batch read up to 200 files by ID in one call. Returns per-file annotated records, an aggregate
Takes no parameters.
Example callreturns →
Return everything ABOUT a file without pulling its content (no token cost from the body). Tags, size, est_tokens, history depth, related-file ids, backlinks, project, folder, last edited. Operates locally with no auth or rate limits. Use this when you
Takes no parameters.
Example callreturns →
Return a 1-indexed inclusive line slice of a file. Out-of-range bounds clamp silently to the file
Takes no parameters.
Example callreturns →
Match a JS regex against one file
Takes no parameters.
Example callreturns →
Match a JS regex against the body of every file in scope (project, KB, or all) and return per-file hits with line numbers. Slower than FTS
Takes no parameters.
Example callreturns →
Update the entire content of an existing file by its ID. This replaces the file
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
List file metadata with optional filters (project_id, tag, favorite, folder, untagged) and pagination. Read-only; no side effects, auth, or rate limits. Each row is annotated with tags, est_tokens, and size_bytes; the response includes
Takes no parameters.
Example callreturns →
Full-text (SQLite FTS5) keyword search across files. Returns ranked matches with inline match_excerpt and title_highlight (no follow-up
Takes no parameters.
Example callreturns →
Run an FTS search and concatenate matched bodies into a single prompt-ready bundle (XML
Takes no parameters.
Example callreturns →
Append tags to ONE file. Additive \u2014 existing tags are preserved; re-adding an existing tag is a no-op (idempotent per tag). New tag names auto-create rows in the global
Takes no parameters.
Example callreturns →
Detach one or more tag IDs from ONE file. Destructive on the link only \u2014 does NOT delete the file or the global tag definition (orphan tags survive in
Takes no parameters.
Example callreturns →
Set or clear the favorite flag on one file (idempotent \u2014 re-setting the same value is a no-op; not a toggle, you pass the desired state). Persists to local SQLite. No external auth or rate limits. Returns
Takes no parameters.
Example callreturns →
List every tag in the global SQLite database with id, name, and applied count. Read-only; no side effects, auth, or rate limits. Returns the entire taxonomy (not paginated). Use to discover existing labels before tagging (so you reuse rather than fork) or to find tag IDs to feed into
Takes no parameters.
Example callreturns →
List every registered project with id, name, absolute path, and a derived
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Write or update the kontexta workflow rules block in a project
Takes no parameters.
Example callreturns →
COPY existing agent context files (CLAUDE.md, AGENTS.md, .cursor/rules/*.mdc, etc.) from a project
Takes no parameters.
Example callreturns →
SIDE-EFFECTFUL \u2014 TOUCHES THE NETWORK. Sync the project
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Return the git commit history for one file (newest first), each entry with hash, message, date, and author. Reads the file
Takes no parameters.
Example callreturns →
Return the unified diff of one file between two commit hashes (typically obtained from
Takes no parameters.
Example callreturns →
DESTRUCTIVE. Overwrite a file
Takes no parameters.
Example callreturns →
Return a flat list of markdown headings for one file (level, text, line, byteStart, byteEnd). Read-only; no side effects, auth, or rate limits. Use as a cheap probe before
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Surgical write \u2014 replace the body of ONE heading without touching siblings. The heading line itself is preserved verbatim; only its body is rewritten. Persists via the same path as
Takes no parameters.
Example callreturns →
List folder paths under a project root (or the Knowledge Base when
Takes no parameters.
Example callreturns →
Create a folder under a project root or the KB. Idempotent \u2014 creating an existing folder succeeds. Nested paths like
Takes no parameters.
Example callreturns →
DESTRUCTIVE \u2014 recursively delete a folder under the KB AND every file inside it (disk + FTS rows). REFUSES (returns isError) when
Takes no parameters.
Example callreturns →
Move/rename a file. Destination
Takes no parameters.
Example callreturns →
Find other files sharing tags with the given file, ranked by
Takes no parameters.
Example callreturns →
Batch variant of
Takes no parameters.
Example callreturns →
DESTRUCTIVE batch \u2014 delete up to 500 files by ID in one call. Same physical-deletion rules as
Takes no parameters.
Example callreturns →
Bulk-tag \u2014 run an FTS
Takes no parameters.
Example callreturns →
Look up a file by its absolute on-disk path and return the same shape as
Takes no parameters.
Example callreturns →
Aggregate counts for a scope:
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Diagnose drift between one file
Takes no parameters.
Example callreturns →
Reconcile the FTS index against disk. For a project (
Takes no parameters.
Example callreturns →
List files created or modified since a checkpoint.
Takes no parameters.
Example callreturns →
List of all registered projects
Takes no parameters.
Example callreturns →
List every Hands command tool currently registered, with project scope, tool name, danger level, confirmation flag, and description. Hands tools come from per-project
Takes no parameters.
Example callreturns →
Re-scan every registered project
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Return the complete authoring reference for
Takes no parameters.
Example callreturns →
Return the user profile stored in the Knowledge Base. The profile helps AI agents understand the user
Takes no parameters.
Example callreturns →
Standardmost installed
$15 / month
- 12,000 calls a month, included
- 144 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Scale
$59 / month
- 100,000 calls a month, included
- 1,200 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
No call is billed on its own, and this plan carries no monthly call limit. $15 a month covers every tool at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 90 / 100
Release 4.4.0 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score96
Client score90
Findings7 threat · 6 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest9e20ee44121c0e0aa5ec26f2a0569a10d2e020d9c018dfe96b126d8ee9423b1a
Score vectorthreat 96 → client 90
| Term | Level | What it prices | Points |
|---|---|---|---|
| −3.6 | |||
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (66 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| journal_note | no tags | |
| journal_intent | no tags | |
| distill_journal | no tags | |
| journal_status | no tags | |
| distill_journal_commit_upgrades | no tags | |
| housekeep_journal | no tags | |
| calendar_add_entity | no tags | |
| calendar_update_entity | no tags | |
| calendar_delete_entity | no tags | |
| calendar_list_entities | no tags | |
| calendar_link_entities | no tags | |
| calendar_add_event | no tags | |
| calendar_update_event | no tags | |
| calendar_delete_event | no tags | |
| calendar_list_events | no tags | |
| calendar_conflicts | no tags | |
| calendar_export_ics | no tags | |
| journal_append | no tags | |
| create_file | file-write | |
| read_file | sensitive-source | |
| read_files | sensitive-source | |
| describe_file | no tags | |
| read_file_lines | sensitive-source | |
| grep_in_file | no tags | |
| regex_search | no tags | |
| update_file | no tags | |
| delete_file | file-write | |
| list_files | sensitive-source | |
| search | no tags | |
| bundle_search | no tags | |
| add_tags | no tags | |
| remove_tags | no tags | |
| set_favorite | no tags | |
| list_tags | no tags | |
| list_projects | no tags | |
| register_project | no tags | |
| onboard_agent | no tags | |
| transfer_agent_context | no tags | |
| commit_backup | no tags | |
| clip_url | no tags | |
| get_history | no tags | |
| get_diff | no tags | |
| restore_file | no tags | |
| read_file_outline | sensitive-source | |
| read_section | no tags | |
| update_file_section | no tags | |
| list_folders | no tags | |
| create_folder | no tags | |
| delete_folder | no tags | |
| move_file | file-write | |
| find_related | no tags | |
| create_files | file-write | |
| delete_files | file-write | |
| tag_search_results | no tags | |
| read_file_by_path | sensitive-source | |
| stats | no tags | |
| suggest_tags | no tags | |
| diff_against_disk | no tags | |
| refresh_index | no tags | |
| whats_new | no tags | |
| project_map | no tags | |
| list_hands | no tags | |
| reload_hands | no tags | |
| confirm_hand | no tags | |
| describe_hands_schema | no tags | |
| get_profile | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest9e20ee44121c0e0a
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 4.4.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
4.4.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Kontexta in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.