Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Senrelay (ContextCore) 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.
What it does
Local macOS multi-agent session relay (/contextcore), source-linked memory, and 15-host MCP sync.
Quickstart
Install it the way its author documents:
The full guide: https://github.com/qingsongcui/ContextCore/releases/download/v1.0.0-beta.2/senrelay-contextcore-mcp.mcpb
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Senrelay (ContextCore) 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. Its scan result is on the Security tab — read the surface before you approve it.
Install it the way its author documents:
The full guide: https://github.com/qingsongcui/ContextCore/releases/download/v1.0.0-beta.2/senrelay-contextcore-mcp.mcpb
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Proactively load minimal project-scoped constraints, active working task state, relevant lessons, and pending conflicts before substantive work.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cwd | string | no | — |
| project_id | string | no | — |
| query | string | no | — |
| task_id | string | no | — |
| session_key | string | no | — |
| max_tokens | integer | no | — |
Search active ContextCore memories and documents (FTS5/hybrid ranked, zero read_count boost).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| project_id | string | no | — |
| category | string | no | — |
| limit | integer | no | — |
Assemble traceable relevant context; character estimates are not billed tokens.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_query | string | yes | — |
| project_id | string | no | — |
| max_tokens | integer | no | — |
| handoff_id | string | no | — |
| context_mode | string | no | — |
Acknowledge context pack receipt so subsequent calls in the same epoch avoid re-sending identical memories.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pack_id | string | yes | — |
Retrieve high-level project brief including active working tasks, pending conflicts, and active decisions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
Create a structured handoff card for target agent. Status remains awaiting_confirmation until explicitly confirmed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target_agent | string | yes | — |
| project_id | string | no | — |
| task_id | string | no | — |
| conversation_id | string | no | — |
| query | string | no | — |
| source_agent | string | no | — |
| language | string | no | — |
Confirm a handoff card to transition status from awaiting_confirmation to confirmed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| handoff_id | string | yes | — |
| confirmed | no | — |
Read a handoff card addressed to this Agent. Unconfirmed cards return a readback-only payload; never confirms on its own.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| handoff_id | string | yes | — |
| language | string | no | — |
Read complete content, provenance and current version before editing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Versioned human-requested edits from Agent conversation, shared with web.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| expected_version | integer | yes | — |
| title | string | no | — |
| content | string | no | — |
| category | string | no | — |
| tags | array | no | — |
| project_id | string | no | — |
| applicability | object | no | — |
Save a governed long-term memory item. Routes temporary task constraints ('这次先别...') to working_tasks and blocks unconfirmed proposals/guesses/raw logs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
| title | string | no | — |
| content | string | no | — |
| category | string | no | — |
| tags | array | no | — |
| supersedes_id | string | no | — |
| cwd | string | no | — |
| scope | string | no | — |
| ambiguous | boolean | no | — |
| pinned | boolean | no | — |
| applicability | object | no | — |
| origin_authority | string | no | — |
| is_user_correction | boolean | no | — |
| cited_memory_ids | array | no | — |
Create or update a short-term working task (6 structured slots, execution_mode, and cited_memory_ids).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | — |
| project_id | string | no | — |
| task_id | string | no | — |
| cwd | string | no | — |
| git_branch | string | no | — |
| status | string | no | — |
| execution_mode | string | no | — |
| goal | string | no | — |
| completed_steps | array | no | — |
| add_completed_step | string | no | — |
| current_state | string | no | — |
| temp_constraints | array | no | — |
| add_temp_constraint | string | no | — |
| failed_attempts | array | no | — |
| add_failed_attempt | string | no | — |
| blockers | array | no | — |
| add_blocker | string | no | — |
| next_steps | array | no | — |
| source_conversation_id | string | no | — |
| cited_memory_ids | array | no | — |
Promote a verified task outcome into conditional long-term memory (requires non-empty applicability).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_id | string | yes | — |
| title | string | yes | — |
| content | string | yes | — |
| applicability | object | yes | — |
| category | string | no | — |
| evidence_quote | string | no | — |
| tags | array | no | — |
| pinned | boolean | no | — |
| complete_task | boolean | no | — |
Explicitly record that loaded memories were genuinely used as basis for work or decisions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| memory_ids | array | yes | — |
| reason | string | no | — |
| task_id | string | no | — |
| conversation_id | string | no | — |
Mark an obsolete memory item as outdated so it stops being injected while remaining traceable.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| memory_id | string | yes | — |
| reason | string | no | — |
| expected_version | integer | no | — |
Update a working task or legacy task while preserving CAS semantics.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_id | string | yes | — |
| status | string | yes | — |
| expected_version | integer | yes | — |
| detail | string | no | — |
Resolve a conflict between existing and proposed memory (keep, replace, merge, or both).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conflict_id | string | yes | — |
| resolution | string | yes | — |
| expected_version | integer | no | — |
| confirmed | no | — |
Permanently delete the confirmed version returned by the latest readback.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| confirmed | boolean | no | — |
| expected_version | integer | no | — |
Import a text note as a document in ContextCore.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| title | string | yes | — |
| text | string | yes | — |
| tags | array | no | — |
Retrieve honest status of ContextCore services, adapters, and background capture.
Takes no parameters.
Read a versioned evidence passage; stale or deleted sources cannot be revived.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| evidence_id | string | yes | — |
| offset | integer | no | — |
| limit | integer | no | — |
Page stored full-transcript messages (0-based ordinal offset) for a conversation identified by exact conversation_id or unambiguous native external_id/UUID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | string | yes | — |
| offset | integer | no | — |
| limit | integer | no | — |
Request background refresh and page indexed conversations, newest first. sync_pending means newer sessions may still be importing; unlinked records are labeled separately. Use next_offset and exact conversation_id/native external_id to select.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| language | string | no | — |
| cwd | string | no | — |
| project_id | string | no | — |
| offset | integer | no | — |
Page stored conversation metadata with exact total_candidates/omitted_count while background refresh proceeds. sync_pending is not an empty native history; unknown-project sessions are labeled separately.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| language | string | no | — |
| cwd | string | no | — |
| project_id | string | no | — |
| offset | integer | no | — |
One-step conversation-first relay for /contextcore:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | string | no | — |
| query | string | no | — |
| max_tokens | integer | no | — |
| language | string | no | — |
| cwd | string | no | — |
| project_id | string | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
Sync recent conversations across all supported agents and return a summarized candidate list of projects for relay.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| language | string | no | — |
Relay a project from recent cross-agent conversations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
| context_mode | string | no | — |
| task_id | string | no | — |
| conversation_id | string | no | — |
| query | string | no | — |
| max_tokens | integer | no | — |
| language | string | no | — |
Companion implicit automatic memory summarization during conversation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
| conversation_id | string | no | — |
| session_summary | string | no | — |
| memories | array | no | — |
| messages | array | no | — |
| cwd | string | no | — |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Senrelay (ContextCore) or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tools were statically extracted from the published source (28 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 |
|---|---|---|
| bootstrap_working_memory | no tags | |
| search_memory | no tags | |
| assemble_context | no tags | |
| get_project_brief | no tags | |
| read_handoff | no tags | |
| read_memory | no tags | |
| get_system_status | no tags | |
| read_evidence | no tags | |
| read_conversation_messages | no tags | |
| ack_context | state-write | state-write: declares readOnlyHint: false |
| start_handoff | state-write | state-write: declares readOnlyHint: false |
| confirm_handoff | state-write | state-write: declares readOnlyHint: false |
| edit_memory | state-write | state-write: declares readOnlyHint: false |
| save_memory | state-write | state-write: declares readOnlyHint: false |
| upsert_working_task | state-write | state-write: declares readOnlyHint: false |
| promote_task_lesson | state-write | state-write: declares readOnlyHint: false |
| cite_memory | state-write | state-write: declares readOnlyHint: false |
| mark_memory_outdated | state-write | state-write: declares readOnlyHint: false |
| update_task_progress | state-write | state-write: declares readOnlyHint: false |
| resolve_conflict | state-write | state-write: declares readOnlyHint: false |
| delete_memory | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| import_note | state-write | state-write: declares readOnlyHint: false |
| discover_relay_conversations | state-write | state-write: declares readOnlyHint: false |
| list_relay_conversations | state-write | state-write: declares readOnlyHint: false |
| relay_conversation | state-write | state-write: declares readOnlyHint: false |
| list_relay_projects | state-write | state-write: declares readOnlyHint: false |
| relay_project | state-write | state-write: declares readOnlyHint: false |
| auto_summarize_memory | state-write | state-write: declares readOnlyHint: false |
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
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
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 1.0.0-beta.2.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Senrelay (ContextCore) can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.