Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.entire-vc/evc-mesh-mcp

MCPB · EVC-MESH-MCP-0.1.8.MCPB · 4 COMPONENTS

Tasks, comments, shared memory and handoffs for teams of people and AI agents, over MCP.

0 this week 52 Trust /100

Last scanned (16 hours ago)

Scores higher than 83% of MCPB servers

Category Project Management

Trust breakdown (7 categories)

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 Security0
  • No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
  • Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
Provenance & Transparency45
Schema Quality & AI Usability59
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 11797 tokens (~327/item across 36 items; 36 tools + 0 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 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 Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 36 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

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.

What we tested

Checks we ran (12)

  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (4)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  • Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  • Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
  • Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 14 Nov 26 0
    • Schema quality: 7851 → 11550 ▼ functional
  • 12 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Nov 26 −3
    • Stability: pass → 0.80 functional
  • 31 Oct 26 +1
    • Stability: 0.97 → pass security
Diagnostics

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 21 Nov 2026 · Analysed mcpb/https://github.com/entire-vc/evc-mesh-mcp/releases/download/v0.1.8/evc-mesh-mcp-0.1.8.mcpb

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem mcpb
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 36 exposed · ~11,797 tokens

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 →

Tool Tokens
add_comment ~362

Add a comment to a task. Response is lean by default: id/author/created_at and the `delivery` report, without echoing the body you just sent; full=true returns the whole comment. If the body @-mentions someone, the response carries a `delivery` array — one entry per mentioned handle — reporting whether it actually reached a path they consume (their task queue, a notification) or was skipped/failed and why; a `hint` field suggests the fix when there is one (e.g. assign the task). Omitted entirely when the comment mentions nobody.

NameTypeReqDescription
bodystringyesComment body (markdown supported).
fullboolean–Return the whole created comment (body echo included) instead of the lean confirmation.
is_internalboolean–Mark as internal (agent-only visible).
metadataobject–Additional metadata as key-value pairs. Set {"informational": true} on a comment you write on a task that is ALREADY done/cancelled when your comment needs no action from its assignee — a plain ackno…
parent_comment_idstring–Parent comment ID for threading.
task_idstringyesTask ID.

No output schema declared.

No examples provided.

add_note ~157

Write a note on a card that wakes nobody: no mention or handoff delivery, no outcome, the checkout untouched. For progress logs and findings that need no action; a note does not end your turn — finish it with wait_for, continue_next, ask_agent, ask_human, finish_task or hand_off.

NameTypeReqDescription
session_idstring–Optional runner session id (max 200 chars), copied onto the recorded outcome and wait.
task_idstringyesThe card to write the note on (UUID or 6-12 hex short id).
textstringyesNote body in markdown.
turn_idstring–Optional turn id within the session (max 200 chars), copied onto the outcome.

No output schema declared.

No examples provided.

add_vcs_link ~771

Link a task to a pull request, commit, or branch. The link is the task↔PR join that PR-driven status automation and 'what shipped for this task?' reports read. Only task_id and url are needed — provider, link_type and external_id are inferred from a GitHub or GitLab URL. The optional status parameter ('merged' or 'closed') records a PR that was already merged or closed before it was linked. Without it the link starts as 'open', and the done-evidence gate blocks move→done on it, since no GitHub webhook fires for a merge that happened before the link existed.

NameTypeReqDescription
acceptance_bystring–Who accepted.
acceptance_evidence_urlstring–Link to the acceptance proof.
acceptance_resultstring–Delivery state: live acceptance result, passed or failed — separate from CI and deploy. Add acceptance_by, acceptance_evidence_url and acceptance_sha for who, proof and the commit it covered.
acceptance_shastring–Commit the acceptance covered, 40 hex.
ci_pipeline_idnumber–Pipeline id of the CI verdict.
ci_shastring–Commit the CI verdict ran on, 40 hex.
ci_statusstring–Delivery state: CI verdict status (pending, running, success, failed, canceled, skipped, manual). Use ci_pipeline_id and ci_sha for the pipeline and commit it ran on.
deployed_atstring–RFC3339 deploy time; defaults to now.
deployed_shastring–Delivery state: the commit now running in `environment`, 40 hex. Requires environment. The link counts as shipped only when this equals merged_sha on environment=prod. Reporting the same sha and envi…
environmentstring–Environment of deployed_sha, e.g. prod or staging.
external_idstring–PR number, commit SHA, or branch name. Inferred from the URL; only needed when the URL is not a recognised PR/commit/branch link.
implementation_shastring–Delivery state (pr links): the commit the change was implemented at, 40 hex.
link_typestring–What the URL points at: pr (alias: pull_request), commit, branch. Inferred from the URL path; defaults to pr.
merged_shastring–Delivery state: the commit the MR merged as on the target branch, 40 hex.
providerstring–VCS provider: github, gitlab. Inferred from the URL host; defaults to github.
rolestring–'review' (the only value) marks the PR as the subject this task reviews or signs off, not the task's own work: its being unmerged no longer blocks move→done. Never set it on the PR that implements th…
statusstring–PR status, if you already know it: open, merged, closed. Pass 'merged' when linking a PR that was merged before this call — that is the one case a webhook can never backfill. Omit it to let the link…
task_idstringyesTask ID.
titlestring–Human-readable label, e.g. the PR title.
urlstringyesLink URL, e.g. https://github.com/owner/repo/pull/123.

No output schema declared.

No examples provided.

answer_decision ~110

Answer a decision request another agent addressed to you: writes the answer as a comment on the asking card, marks the request answered and wakes the asker. Only the addressee or a person may answer; an answered or withdrawn request is refused with 409. Does not touch your own card or checkout.

NameTypeReqDescription
answerstringyesYour answer, max 4000 chars: the choice and the reason.
request_idstringyesDecision request id, as given in the question you received.

No output schema declared.

No examples provided.

archive_memory ~278

Take a stale memory out of recall and get_memory WITHOUT deleting it (archived=true), or bring it back (archived=false). The reason is required and stored on a revision. Allowed for whoever may write to the memory's scope: any agent with write access to the project for a project entry (not only its author), only the owner for an agent entry, leads for a workspace entry. Archived entries stay readable with include_archived=true. A repeat remember on an archived key updates it but keeps it archived. Prefer this to forget and to a short expires_at for anything that may be needed again.

NameTypeReqDescription
archivedboolean–true archives (default), false restores.
keystring–Exact key, used when memory_id is not given. Refused with the candidates listed if it names several entries; narrow with scope/project_id.
memory_idstring–UUID of the memory (the id field of recall full=true). Either memory_id or key is required.
project_idstring–Narrows a key lookup to one project.
reasonstringyesWhy the entry leaves (or returns to) recall, up to 500 characters, e.g. 'MR merged and released; directive no longer applies'.
scopestring–Narrows a key lookup: workspace, project or agent.

No output schema declared.

No examples provided.

ask_agent ~254

End your turn with a question only another agent can answer: opens a decision request to that agent (or returns your identical open one), records a wait on it, writes the comment and releases your checkout; you are woken when they answer. A question this agent already answered on this card is refused with already_answered (nothing written, checkout kept): read that answer, and if you still need one, ask a new question that says what changed. The addressee must be an agent of the team directory, not a person (ask_human) and not yourself. Work another agent must do is hand_off, not a question.

NameTypeReqDescription
questionstringyesThe question with the options you see, max 4000 chars.
session_idstring–Optional runner session id (max 200 chars), copied onto the recorded outcome and wait.
task_idstringyesThe card the question is about (UUID or 6-12 hex short id).
tostringyesAgent name or UUID from get_team_directory; an @-handle prefix is not needed.
turn_idstring–Optional turn id within the session (max 200 chars), copied onto the outcome.

No output schema declared.

No examples provided.

ask_human ~342

End your turn with a question only a person can answer: posts it as a Blocking question to that person, which arms the card's human gate and notifies them, records your wait on the answer and releases your checkout; you are woken when the gate is lifted. Refused, with nothing posted, when to is not a person of the workspace or the previous question already has an answer (name what is new in supersedes). A question to an agent is ask_agent.

NameTypeReqDescription
canonical_keystring–Names the question; an existing recorded decision under the same key refuses the ask.
deadlinestring–When the default applies: RFC3339 with Z or an offset, in the future.
questionstringyesThe question with the options you see, max 2000 chars.
recommended_defaultstring–What you will do if nobody answers by the deadline; one line, max 500 chars.
session_idstring–Optional runner session id (max 200 chars), copied onto the recorded outcome and wait.
softboolean–true: the gate may be released by the default-on-timeout sweep. Default false (hard).
supersedesstring–What the previous, already answered, question did not cover; one line.
task_idstringyesThe card the question is about (UUID or 6-12 hex short id).
tostringyesThe person's username, e.g. alex; an @ prefix is not needed.
turn_idstring–Optional turn id within the session (max 200 chars), copied onto the outcome.

No output schema declared.

No examples provided.

assign_task ~123

Assign a task to a user or agent. Returns a lean confirmation by default (id, status_id, assignee, updated_at); full=true returns the whole task.

NameTypeReqDescription
assign_to_selfboolean–Assign to the calling agent.
assignee_idstring–Assignee UUID. Omit to unassign.
assignee_typestring–Assignee type: user, agent.
fullboolean–Return the complete task (all fields, verbatim) instead of the lean confirmation.
task_idstringyesTask ID.

No output schema declared.

No examples provided.

clear_start_after ~291

Clear a card's start_after only if it is still exactly the schedule you read (compare-and-clear). Pass the start_after, version, start_after_origin and start_after_receipt_id from get_task. A changed card is refused with 409 cas_conflict and its current values — nothing is written; re-read before deciding anything. Repeating a call with the same idempotency_key returns the first receipt (replayed=true). Does not touch human gates, dependencies, waits or due_date.

NameTypeReqDescription
expected_originstring–The card's start_after_origin as you read it: agent_evidence, human_explicit or legacy_unknown. Required for an agent.
expected_start_afterstringyesThe card's start_after as you read it, RFC3339.
expected_versionnumberyesThe card's version as you read it.
idempotency_keystring–Key of this clear, max 200 chars; reuse it when you repeat the same call. Generated when omitted.
reasonstring–Why the date is no longer needed, max 500 chars; stored on the clear receipt.
schedule_receipt_idstring–The card's start_after_receipt_id as you read it. Required for an agent unless the origin is legacy_unknown.
task_idstringyesThe card (UUID or 6-12 hex short id).

No output schema declared.

No examples provided.

continue_next ~169

End your turn with a piece of work done and more to do right away: records the outcome and the comment, keeps the card with you and extends your checkout. Reading the card or writing a plan is not a piece of work — keep working instead. Refused with 409 when you do not hold the card's checkout.

NameTypeReqDescription
notestringyesWhat was done this turn and what comes next, max 4096 chars.
session_idstring–Optional runner session id (max 200 chars), copied onto the recorded outcome and wait.
task_idstringyesThe card you are working on (UUID or 6-12 hex short id).
turn_idstring–Optional turn id within the session (max 200 chars), copied onto the outcome.

No output schema declared.

No examples provided.

create_task ~411

Create a new task in a project and return it with its id. status_slug sets the initial status (defaults to the project's first status); assignee_id with assignee_type routes it to someone; parent_task_id makes it a subtask. Search list_tasks first so you do not file a duplicate.

NameTypeReqDescription
assignee_idstring–Assignee ID (user or agent UUID).
assignee_typestring–Assignee type: user, agent.
custom_fieldsobject–Custom field values as key-value pairs.
delegation_levelstring–Delegation level: auto, review, supervised.
descriptionstring–Task description.
due_datestring–Due date in RFC3339 format.
estimated_hoursnumber–Estimated hours for the task.
labelsarray–Task labels.
parent_task_idstring–Parent task ID for subtask.
prioritystring–Priority: urgent, high, medium, low, none.
project_idstringyesUUID of the project to create the task in (list_projects returns ids).
start_afterstring–Hold the task out of the queue until this moment, RFC3339 with Z or an offset (2026-11-01T09:00:00+03:00). From an agent it must be the published time of an external event, given with start_after_evi…
start_after_evidenceobject–Required by the server for an agent's start_after: {event_ref, source, why}, the same rules as wait_for on=time.
start_after_originstring–Optional, only agent_evidence. The server derives the origin from the caller; a person's date needs no evidence.
status_slugstring–Status slug (e.g. 'todo'). Uses project default if omitted.
titlestringyesTask title.

No output schema declared.

No examples provided.

finish_task ~251

Close the card with its result: sets result_kind, moves the card to done (or review, when someone must accept a live result), writes the evidence as the closing comment, cancels your active wait and releases your checkout. Both result_kind and evidence are required; the existing move gates (closing comment length, linked MRs merged, open subtasks) still apply and their refusals are returned as is.

NameTypeReqDescription
evidencestringyesProof of each acceptance criterion — commands and their quoted output, max 4096 chars.
evidence_linksarray–Optional URLs backing the evidence (MR, pipeline, artifact).
result_kindstringyesWhat the card delivered: change, defect, research, content or ops.
session_idstring–Optional runner session id (max 200 chars), copied onto the recorded outcome and wait.
task_idstringyesThe card to close (UUID or 6-12 hex short id).
tostring–Target status: done or review. review means the result is live and awaits someone's acceptance.
turn_idstring–Optional turn id within the session (max 200 chars), copied onto the outcome.

No output schema declared.

No examples provided.

forget ~80

Permanently delete one memory entry by its UUID. Agents can only delete their own agent-scope memories; project and workspace memories are refused. To correct an entry, call remember with the same key instead of deleting it.

NameTypeReqDescription
memory_idstringyesUUID of the memory to delete: the id field of a recall(full=true) result, not its key.

No output schema declared.

No examples provided.

get_canonical_updates ~133

Fetch canonical decisions broadcast since a given time. Returns only privacy:public records targeted at you or all agents. A change feed for session start; get_canonical searches the canonical layer by topic.

NameTypeReqDescription
agentstring–Your agent slug (e.g. 'alice'). Used to filter propagate_to:<slug> records. Omit to get only propagate_to:all records.
scopestring–Optional project UUID to restrict to project-scoped decisions.
sincestring–RFC3339 cursor. Defaults to your previous session's start time (server-resolved). Omit on first call.

No output schema declared.

No examples provided.

get_context ~137

Get RECENT ACTIVITY for a project (last 24h by default): event stream with summaries, decisions, errors, plus accumulated project knowledge. Use it for "what changed lately"; get_project_knowledge returns the durable facts, recall searches memory for one fact.

NameTypeReqDescription
event_typesarray–Filter by event types.
limitnumber–Max events to return (default 50).
project_idstringyesUUID of the project whose recent activity to read (list_projects returns ids).
sincestring–Only events after this timestamp (RFC3339).
tagsarray–Filter by tags.

No output schema declared.

No examples provided.

get_memory ~228

Full text of ONE memory by exact key (the `key` field recall returns). Returns the full content of an entry whose recall result ends with the `…` cut marker. Errors if no entry has exactly that key. Archived and expired entries are hidden unless include_archived / include_expired is set.

NameTypeReqDescription
include_archivedboolean–Also look among archived memories (default false).
include_expiredboolean–Also look among memories past their expires_at (default false). An expired entry is hidden from recall and get_memory the moment it expires and stays readable with this flag until the background clea…
keystringyesExact memory key, as returned by recall.
project_idstring–Project of a project-scoped entry, if the key exists in several.
scopestring–Filter by scope: workspace, project, agent, or all (default).

No output schema declared.

No examples provided.

get_my_rules ~113

Get ALL governance rules that apply to you: workflow constraints, assignment policies, behavioral requirements. Includes workspace and project-level rules with source annotations. This is the one to call before acting in a project: get_project_rules lists every rule configured there whoever it targets, get_assignment_rules and get_workflow_rules return a single rule family.

NameTypeReqDescription
project_idstring–Optional project UUID. With it, returns the effective rules for that project (workspace rules merged with the project's own); without it, workspace-level rules only.

No output schema declared.

No examples provided.

get_my_tasks ~391

Get YOUR assigned tasks, non-blocking. Use list_tasks to browse or search other people's tasks in a project, poll_tasks only to block until a new assignment arrives. Filterable by status_category to focus on active work. Default (cold) view is compact: only in_progress, review and the top 5 todo are requested and listed (envelope `omitted` counts the todo past the cap, has_more flags open cards past limit; done, cancelled and backlog need full=true or status_category), descriptions are omitted (has_description marks them; get_task(id) or full=true returns the full text). Envelope fields (created_by/created_at, assignee_id) and valueless fields (0-counters, due_date=null, human_gate=false) are omitted; full=true returns the complete items and get_task returns one card's full details.

NameTypeReqDescription
accept_deltaboolean–Opt in to lossless delta against known_revision: complete changed items, removed_ids, full order and non-items envelope. Apply only to the retained matching base; otherwise omit known_revision and re…
fullboolean–Return complete non-capability REST fields; always bypasses revision and delta shortcuts.
known_revisionstring–Revision of a complete snapshot retained for this session and the same filters/view. Omit after cache loss, restart or compaction to request complete cold. Exact match returns unchanged=true; mismatc…
limitnumber–Max results (default 50).
project_idstring–Filter by project.
snapshot_sessionstring–Opaque non-secret consumer cache namespace. Required for conditional responses on stateless HTTP. Use a fresh value after restart or compaction; never credentials or lease tokens.
status_categorystring–Filter by status category: backlog, todo, in_progress, review, done, cancelled.

No output schema declared.

No examples provided.

get_project_knowledge ~199

Get the PERMANENT KNOWLEDGE of a project: decisions, conventions, accumulated context. Returns workspace-level + project-level memories (workspace tier paged by limit/offset and narrowed by min_importance and tags_any). Use it for the standing picture of ONE project; get_context returns what happened recently, recall searches all memory for one specific fact, get_canonical returns owner-curated decisions on a topic.

NameTypeReqDescription
limitnumber–Max workspace-tier memories (default 100, max 500).
min_importancenumber–Minimum importance_score for workspace-tier (default 0 = all).
offsetnumber–Pagination offset for workspace-tier (default 0).
project_idstringyesUUID of the project whose knowledge to load (list_projects returns ids).
tags_anystring–Comma-separated tag OR-filter for workspace-tier, e.g. 'kind:decision,kind:incident'.

No output schema declared.

No examples provided.

get_task ~688

Get task details: compact decision fields, active human_gate=true and status slug; descriptions and ordinary comment bodies are always complete. Comment IDs support reply/after; timestamps are UTC to the minute. Known automation comments are one-line summaries (include_auto=true restores their complete bodies). full=true restores non-capability REST fields. If status lookup is unavailable, status_id and an explicit status_lookup_error remain. Comments return the newest comments_limit entries (default 5, max 200) with pagination markers. since=RFC3339 (from task.updated_at) skips an unchanged task and older comments. In a stdio session a repeat read of the same card returns only what changed since that session last read it (unchanged card: stub with task_changed=false; unchanged description omitted with description_unchanged=true; comments already returned are dropped, counted in comments_already_shown); full=true always returns everything.

NameTypeReqDescription
comments_limitnumber–How many of the NEWEST comments to include when include_comments=true (default 5, max 200). The tail is where an acting agent looks first; raise it when you need more of it. The API caps any single r…
fullboolean–Return the task (full description, non-capability fields, whole inline comments) instead of the compact view (default false).
include_artifactsboolean–Include artifacts.
include_autoboolean–Return complete automation bodies in compact mode (ordinary comments are always complete).
include_commentsboolean–Include the task's most recent comments (see comments_limit for how many; the response carries comments_total_count and comments_has_more so a longer thread is never silently hidden).
include_dependenciesboolean–Include dependencies.
include_vcs_linksboolean–Include linked PRs/MRs/commits/branches (id, provider, link_type, external_id, url, status, created_at, plus delivery{implementation_sha, ci_verdict, merged_sha, deployed, acceptance} and a derived i…
sincestring–RFC3339 timestamp from an earlier call in this session (e.g. that response's task.updated_at, or your own last-call time). With it: include_comments returns only comments created after it, and the fu…
task_idstringyesTask ID (full UUID or 6–12 char hex short-ID prefix).

No output schema declared.

No examples provided.

get_task_context ~75

Get EVERYTHING about ONE TASK in a single call: full details + comments + artifacts + dependencies + activity. Combines the results of get_task, list_comments and list_artifacts for one task in a single response.

NameTypeReqDescription
task_idstringyesTask ID (full UUID or 6–12 char hex short-ID prefix).

No output schema declared.

No examples provided.

hand_off ~196

Give the card to another agent who must do the next part: assigns it to them, moves it to todo, writes the comment, cancels your active wait and releases your checkout, in one step instead of assign + move + release. The addressee must be an agent of the team directory. Use ask_agent when you only need their answer and keep the card.

NameTypeReqDescription
session_idstring–Optional runner session id (max 200 chars), copied onto the recorded outcome and wait.
task_idstringyesThe card to hand over (UUID or 6-12 hex short id).
tostringyesAgent name or UUID from get_team_directory who takes the card.
turn_idstring–Optional turn id within the session (max 200 chars), copied onto the outcome.
whystringyesWhat they must do and what is already done, max 4000 chars.

No output schema declared.

No examples provided.

heartbeat ~228

Report that you are alive and what you are working on, so the team directory shows you online or busy and names your current task. Call it at session start and every few minutes during long work. It changes no task and returns no queue: get_my_tasks reads your assignments.

NameTypeReqDescription
agent_typestring–Optional self-report of the harness this agent runs in: claude_code, codex, cursor, copilot, gemini_cli, openclaw, cline, aider, hermes, custom.
current_task_idstring–ID of the task currently being worked on.
messagestring–Short human-readable status message (e.g. 'running tests', 'waiting for review').
metadataobject–Arbitrary JSON metadata to store with the heartbeat.
modelstring–Optional self-report of the model this agent runs on (max 128 chars). Empty string clears it.
statusstring–Agent status shown in the team directory: online, busy or error. Use error only when you cannot work; report_error records why.

No output schema declared.

No examples provided.

list_projects ~99

List the projects in the workspace with their ids, names and slugs. Call it first to find the project_id that most other tools require. Archived projects are hidden unless include_archived=true.

NameTypeReqDescription
include_archivedboolean–Also list archived projects. Default false: only active projects are returned.
workspace_idstring–Workspace UUID. Defaults to the calling agent's workspace; another workspace is only readable if your key belongs to it.

No output schema declared.

No examples provided.

list_tasks ~655

List tasks with strict filters. Provide project_id for a project listing or workspace_id plus search for cross-project search. Unknown parameters and invalid categories are errors. Compact items contain id, title, status slug, priority, assignee_name, labels, updated_at, runtime_state (working/waiting/queued/stopped with since/lane/ref/stale, when known) and routing parent_task_id/start_after when set; workspace results also contain project_id. full=true returns complete REST items; listing descriptions are subject to the API page budget, while get_task returns full details. For your own queue use get_my_tasks.

NameTypeReqDescription
assigneestring–Filter by exact case-insensitive assignee name, UUID, or me. Unknown or ambiguous names are errors.
assignee_idstring–UUID-only compatibility alias for assignee. Use assignee for names or me.
assignee_typestring–Filter by assignee type: user, agent, unassigned.
fullboolean–Return complete items (full descriptions and non-capability envelope fields) instead of compact items.
labelsarray–Filter by labels.
limitnumber–Max results to return (default 20). The compact view caps limit at 50 — a larger value is clamped and the response says so via limit_clamped_to; pass full=true for up to 200 per page.
list_revisionnumber–The list_revision echoed back on a previous page of this same project-scoped walk (see the response's list_revision field). Pass it back to continue that walk. If the project's tasks changed since th…
orderstring–Sort direction: asc (default) or desc. Without this, a project larger than `limit` returns its OLDEST tasks, so "what changed recently" walks come back empty and look clean. An invalid value is REFUS…
pagenumber–1-based page number (default 1). The response reports total_pages; without this parameter every page beyond the first was unreachable while the envelope kept advertising them.
prioritystring–Filter by priority: urgent, high, medium, low, none.
project_idstring–Project ID (required unless workspace_id is provided).
runtime_kindstring–Filter by effective runtime state: working, waiting, queued, stopped. working also matches a card with a live checkout and no reported state, whatever its status.
searchstring–Search in title and description.
sortstring–Sort field: created_at, updated_at, priority, due_date.
status_categorystring–Filter by status category: backlog, todo, triage, in_progress, review, done, cancelled.
workspace_idstring–Workspace ID for global cross-project search (requires search parameter).

No output schema declared.

No examples provided.

move_task ~233

Change task status (e.g. todo → in_progress → done). Status is given as a slug (not a UUID). On move to 'review', task auto-reassigns to creator unless assignee_id is provided. Returns {task, new_status} with a lean task by default (id, status_id, assignee, updated_at — the post-move assignee is always included so an auto-reassign is visible); full=true returns the whole reloaded task.

NameTypeReqDescription
assignee_idstring–Reassign to this agent/user on move. Overrides auto-reassign to creator on review.
assignee_typestring–Assignee type if assignee_id is set: user or agent.
commentstring–Optional comment, written before the move so it lands even when the move hands the card (and its lock) to someone else.
fullboolean–Return the whole reloaded task instead of the lean confirmation.
status_slugstringyesTarget status slug (e.g. 'in_progress', 'done').
task_idstringyesTask ID.

No output schema declared.

No examples provided.

publish_event ~172

Publish an event to the event bus. event_type='summary' publishes a summary. Add memory={persist:true, key:'decision-name'} to also save as permanent memory. Replaces the deprecated publish_summary tool.

NameTypeReqDescription
event_typestringyesEvent type: summary, status_change, context_update, error, dependency_resolved, custom.
memoryobject–Optional memory hint to persist alongside the event (e.g. key decisions, conventions).
payloadobjectyesEvent payload as key-value pairs.
project_idstringyesProject ID.
subjectstringyesEvent subject line.
tagsarray–Event tags for filtering.
task_idstring–Related task ID.
ttl_hoursnumber–Time-to-live in hours (default 24).

No output schema declared.

No examples provided.

recall ~819

SEARCH memory by keywords. Finds a SPECIFIC piece of knowledge, e.g. 'API convention' or 'license decision'. Returns ranked results with scores. Default view is compact: per item key, tags, score and the first ~300 chars of content (a trailing … marks a cut; timestamps, scope and bookkeeping fields are omitted). get_memory(key) returns the whole text of one entry; full=true returns every item uncut with all stored fields (created_at included). Below the relevance threshold, returns an empty list with an explanation instead of weak matches. include_archived=true also returns archived memories. Use it to find one fact; recall_with_graph also follows links to related memories, get_project_knowledge pages through one project's permanent knowledge.

NameTypeReqDescription
apply_recency_decayboolean–Sort by relevance * 0.95^days_since_created.
created_bystring–Filter by agent ID (UUID).
fullboolean–Return every item in full, with all stored fields and uncut content (default false: compact view, content cut at ~300 chars and marked with a trailing `…`, bookkeeping fields such as agent_id, worksp…
include_archivedboolean–Also return archived memories (retired by their owner or by review but kept for history). Default false: only live memories.
include_expiredboolean–Also return memories past their expires_at (default false). An expired entry is hidden from recall and get_memory the moment it expires and stays readable with this flag until the background cleanup…
limitnumber–Max results (1–50). Omitted compact requests use 5; full=true or an explicit profile keeps the previous default 10. Existing profile presets still apply when limit is omitted (multi-session uses 20,…
min_importancenumber–Minimum importance_score threshold (0-1, default 0.3 — matches the lowest score the server assigns, kind:session-checkpoint, so prior-session hand-offs are returned without an override). Raise it to…
offsetnumber–Pagination offset (default 0).
order_bystring–Sort order: created_at:desc (default), created_at:asc, relevance:desc, decayed_relevance:desc.
project_idstring–Filter to a specific project.
querystringyesFull-text search query.
recall_profilestring–Override automatic query classification. Existing preset values are preserved; explicit limit takes precedence.
relevance_minnumber–Minimum relevance score (0-1).
scopestring–Filter by scope: workspace, project, agent, or all (default).
sincestring–Return memories created at or after this RFC3339 timestamp.
tagsarray–AND-filter: memory must contain ALL listed tags.
tags_anyarray–OR-filter: memory must contain AT LEAST ONE of these tags.
untilstring–Return memories created at or before this RFC3339 timestamp.

No output schema declared.

No examples provided.

recall_with_graph ~169

Search memory with Knowledge Graph expansion. Seeds from hybrid recall, then BFS-traverses memory_edges up to hops depth. Returns memories ranked by composite score with hop_distance and provenance fields. Returns broader context: related decisions, connected incidents, derived learnings. Slower and wider than recall: use it for the connected context around a topic, recall for a single fact.

NameTypeReqDescription
hopsnumber–Graph traversal depth (default 2, max 5).
project_idstring–Filter to a specific project.
qstringyesSearch query (keywords or natural language).
task_idstring–Optional task ID — used as cache key discriminator for session-scoped traversal.
weight_thresholdnumber–Minimum edge weight to follow (default 0.3).

No output schema declared.

No examples provided.

record_owner_decision ~363

Record a directive from the workspace owner as a canonical decision in project_knowledge. Broadcasts to specified agents via propagate_to tags. privacy:private records are stored but EXCLUDED from get_canonical_updates. Auto-flags private if text contains secrets. If task_id is given, also records this as a human_gate decision on that task (docs/human-gate-decision-recorded.md in evc-mesh) — releases the gate as a consequence if it's currently live, and links back via canonical_key. Best-effort: a failure here is reported in the result but does not undo the canonical write.

NameTypeReqDescription
privacystring–'public' (default, visible in change-feed) or 'private' (recorded but hidden).
propagate_toarray–Agent slugs to propagate to, e.g. ['alice','bob']. Use ['all'] for workspace-wide broadcast.
question_refstring–Optional comment UUID of the Blocking marker this decision answers (only with task_id). Omit when the task has exactly one live marker — the server binds it. Required when several markers are live; t…
scopestring–Optional project_id UUID. Omit for workspace-level decisions.
summarystringyesOne-line summary used as UPSERT key (dedupes same decision on same day).
task_idstring–Optional task UUID this decision answers. When set, also records a human_gate decision on that task (provenance=attested, channel=telegram, quote=text) — releasing a live human_gate as a consequence.…
textstringyesFull text of the decision/directive.

No output schema declared.

No examples provided.

remember ~1,029

Save knowledge to persistent memory. Stores decisions, conventions, preferences. UPSERT by key — calling with same key updates the existing entry. Content is screened on write and REFUSED with a named reason (never silently stripped or stored) if it contains invisible/bidi characters, an LLM role tag, an instruction to ignore previous/system instructions, a PEM private key, a prefixed API token (sk-/ghp_/xox*/AKIA), or a literal assignment to a *_PASSWORD/_SECRET/_TOKEN/_API_KEY name. LIMITATION — this screen is partial and is not a secret filter: it cannot see a secret that has no recognisable prefix and no field name next to it (a bare value pasted on its own line), nor names it does not know. Credentials pasted here are not guaranteed to be caught; content stores where a secret lives, not its value.

NameTypeReqDescription
attach_contextboolean–When false, disables auto-injection of thread_id and source_task_id. Use for cross-cutting records not tied to the active task.
contentstringyesWhat to remember (markdown).
expected_versionnumber–Make the write conditional: it succeeds only if the stored version still matches this number, and is REFUSED with both version numbers if someone else wrote to the key in between. Pass the version re…
expires_atstring–RFC3339 timestamp or Go duration (e.g. '72h') when this memory should expire. Hidden from recall and get_memory the moment it expires; physically deleted by the background cleanup (every 6 h) 7 days…
keystringyesSlug key for UPSERT (e.g. 'api-convention', 'license-decision'). ENFORCED server-side as ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — lowercase alphanumeric and hyphens only, at least two characters, no leading or…
project_idstring–Project ID (required for project scope).
reasonstring–Why this memory is worth writing — what a future thread should be able to do with it, or what changed if you are correcting an existing key. Recorded on the revision alongside the content, so a later…
relevancenumber–Relevance score 0-1 (default 1.0 when omitted). NOT the same field as importance_score: relevance is a caller-set ranking hint, importance_score is computed from tags (see tags) and is the field min_…
scopestring–workspace | project | agent (default: project).
source_task_idstring–UUID of the Mesh task that produced this memory. Auto-populated from the runner state file (FIDDLER_STATE_FILE) or the active checkout. Enables Amendment 2/3 KG edge hooks.
source_urlstring–Optional URL/path to the source of this knowledge (task ID, PR, file path).
tagsarray–Tags for categorization and filtering. A kind: tag also SETS importance_score, which is what decides whether recall returns this entry at its default threshold of 0.3 — so the tag you choose is a ret…
thread_idstring–Thread identifier for same-session memory grouping. Auto-populated from the runner state file when omitted.

No output schema declared.

No examples provided.

report_error ~240

Report a failure you hit while working, so the team sees it instead of it staying in your log. With task_id, publishes an error event (tagged error and the severity, kept 72h) to that task's project, where get_context shows it. With recoverable=false it also sets your agent status to error in the team directory. It does not move the task or comment on it: use add_comment for that.

NameTypeReqDescription
error_messagestringyesWhat went wrong, in a sentence or two. Required and non-empty; its first 100 characters become the event subject.
recoverableboolean–Default true. Pass false when you cannot continue: your agent status is then set to error.
severitystring–Severity: low, medium (default), high or critical. Also added as an event tag.
stack_tracestring–Optional stack trace, command output or other detail, stored in the event payload.
task_idstring–UUID of the task the error belongs to. Without it nothing is published to a project; only the agent status changes (and only when recoverable=false).

No output schema declared.

No examples provided.

session_report ~121

Report token usage and cost at the end of a session. Saves them on your agent session record and returns this session's tool-call stats and a compliance score (whether you loaded project context before acting). All parameters are optional; omitted or zero values are not recorded.

NameTypeReqDescription
estimated_costnumber–Estimated cost in USD.
modelstring–LLM model used (e.g. 'claude-sonnet-4').
tokens_innumber–Total input tokens this session.
tokens_outnumber–Total output tokens this session.

No output schema declared.

No examples provided.

set_project_knowledge ~285

Write a structured fact to project knowledge. UPSERT by key — calling with same key updates the existing entry. Stores deploy URLs, stack conventions, gotchas. These facts are visible via get_project_knowledge.

NameTypeReqDescription
attach_contextboolean–When false, disables auto-injection of thread_id and source_task_id.
categorystring–Optional category: deploy, stack, conventions, gotchas, api, auth, etc.
keystringyesSlug key for UPSERT (e.g. 'deploy-url', 'stack-convention'). Same enforced pattern as remember: ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — hyphens only, no colons; a colon-delimited key is refused, not normalise…
project_idstringyesProject ID to store knowledge for.
source_task_idstring–UUID of the Mesh task that produced this fact. Auto-populated from the runner state file when omitted.
source_urlstring–Optional URL/path to the source of this knowledge.
tagsarray–Additional tags for filtering.
thread_idstring–Thread identifier. Auto-populated from the runner state file when omitted.
valuestringyesThe knowledge to store (markdown, max 4000 chars).

No output schema declared.

No examples provided.

update_task ~367

Update task fields. Returns a lean confirmation by default (id, status_id, assignee, updated_at) — the card's static fields are not echoed back; full=true or get_task returns them.

NameTypeReqDescription
completion_signalboolean–Mark agent-side work as finished.
custom_fieldsobject–Custom field values to update.
delegation_levelstring–Routing after work: auto, review, or supervised.
descriptionstring–New description.
due_datestring–Due date in RFC3339 format. Pass an empty string to clear it.
estimated_hoursnumber–Estimated hours.
fullboolean–Return the complete updated task (all fields, verbatim) instead of the lean confirmation (id, status_id, assignee, updated_at).
labelsarray–New labels.
prioritystring–New priority.
start_afterstring–Hold the task out of the queue until this moment, RFC3339 with Z or an offset (2026-11-01T09:00:00+03:00). From an agent it must be the published time of an external event, given with start_after_evi…
start_after_evidenceobject–Required by the server for an agent's start_after: {event_ref, source, why}, the same rules as wait_for on=time.
start_after_originstring–Optional, only agent_evidence. The server derives the origin from the caller; a person's date needs no evidence.
task_idstringyesTask ID.
titlestring–New title.

No output schema declared.

No examples provided.

wait_for ~1,258

End your turn waiting on an event: another card (on=card), a merge request (on=mr), a CI pipeline or GitHub Actions run (on=pipeline), the runner's merge gate on a reviewed head (on=merge), a runner registration (on=registered), the published moment of an external event (on=time, with event_ref, source and why) or, only on a card a lead labelled wake:manual, a passive wait with no observer and no timer that a new comment or the lead's action ends (on=manual, with note saying why). A GitHub PR merge is on=mr provider=github until=merged (project_path owner/repo, mr_iid the PR number, after_sha the head, after_status opened); on=merge is GitLab only. The server checks the target, records the wait (replacing your previous one on this card), writes the comment and releases your checkout; you are woken when the event happens. A refusal writes nothing. Waiting on another agent's answer is ask_agent; on a person, ask_human.

NameTypeReqDescription
after_pipeline_idnumber–Baseline of until=green or changed: the pipeline id you observed (on=pipeline: equal to pipeline_id). Send with after_sha and after_status.
after_shastring–on=merge, required: full 40 or 64 hex SHA of the reviewed head. on=mr or pipeline, optional baseline: the head SHA you observed.
after_statusstring–Baseline status: opened for until=merged; for until=green or changed the pipeline status you observed (running, failed, success, manual, ...).
criterionstring–on=card with target_condition=artifact_published: the result you wait for, as its producer will name it in the evidence (max 500 chars).
event_refstring–on=time, required: the external event the moment belongs to, e.g. nightly-export (max 500 chars).
mr_iidnumber–on=mr or merge: merge request iid within project_path (not the global id).
notestring–Why you wait and what ends the wait; the generated comment shows it whole, the wait itself keeps its first 500 characters. Required for on=manual.
onstringyesWhat you wait on: card, mr, pipeline, time, merge, registered or manual. Only the fields of that kind are read; after_* and registration* on a kind that does not take them are refused.
pipeline_idnumber–on=pipeline: the pipeline id to wait on.
project_pathstring–on=mr, pipeline or merge: project path, e.g. entire-vc/evc-mesh.
providerstring–on=mr: gitlab or github. on=pipeline: gitlab (default) or github for an Actions run (project_path owner/repo, pipeline_id the run id). on=merge: gitlab only; a GitHub PR merge is on=mr provider=githu…
registrationstring–on=registered: ops-review, gmail, receipt, lifecycle, stall, recovery, queue or native.
registration_refstring–on=registered: ops-review or native: the 64-hex id; gmail: gmr_<12 hex>; receipt, lifecycle, stall, recovery, queue: this card's 8-hex id (may be omitted).
required_jobsarray–on=pipeline, or on=mr with until green or changed: job names to read the wait from; omit for the whole pipeline.
session_idstring–Optional runner session id (max 200 chars), copied onto the recorded outcome and wait.
sourcestring–on=time, required: where the event's time is published: an https:// URL, comment:<uuid> or artifact:<uuid> written by someone else. A card is not a source.
target_conditionstring–on=card: what the card must reach: task_done (default), shipped, deployed, accepted or artifact_published (a named result of that card: give criterion; its owner records the evidence). A card closed…
target_task_idstring–on=card: the card you wait on. Creates or reuses a blocks dependency on it; the receipt's wait names that edge (dependency_id, dependency_generation) and dependency_owned=true only when this wait cre…
task_idstringyesThe card you are working on (UUID or 6-12 hex short id).
turn_idstring–Optional turn id within the session (max 200 chars), copied onto the outcome.
untilstring–on=mr: merged, green or changed. on=pipeline: finished, green or changed.
until_atstring–on=time: when the external event happens, RFC3339 with Z or an offset (2026-10-29T06:00:00Z, 2026-10-29T09:00:00+03:00), 5 minutes to 30 days from now. Not a retry or poll interval: a wait on a card,…
vcs_link_idstring–on=mr: id of a VCS link of this card. Alternative to provider + project_path + mr_iid.
whystring–on=time, required: what happens at until_at and why not earlier, 10 to 500 chars.

No output schema declared.

No examples provided.

Install

How do I install the io.github.entire-vc/evc-mesh-mcp server?

io.github.entire-vc/evc-mesh-mcp ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 1c3a83279cdc188aa484de611e69fdbe5e3de46d7c007cb8cf5ef4f8e3b95aa4; the commands to do that are on this page. If it does not match, do not open it.

mcpb · evc-mesh-mcp-0.1.8.mcpb

Download bundle

Check the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.

SHA-256

1c3a83279cdc188aa484de611e69fdbe5e3de46d7c007cb8cf5ef4f8e3b95aa4

macOS / Linux

echo "1c3a83279cdc188aa484de611e69fdbe5e3de46d7c007cb8cf5ef4f8e3b95aa4  evc-mesh-mcp-0.1.8.mcpb" | shasum -a 256 -c

Windows (PowerShell)

(Get-FileHash -Algorithm SHA256 .\evc-mesh-mcp-0.1.8.mcpb).Hash -eq "1c3a83279cdc188aa484de611e69fdbe5e3de46d7c007cb8cf5ef4f8e3b95aa4"

Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.

Common questions

What is the io.github.entire-vc/evc-mesh-mcp server?

io.github.entire-vc/evc-mesh-mcp is listed in the public MCP registry as io.github.entire-vc/evc-mesh-mcp. Tasks, comments, shared memory and handoffs for teams of people and AI agents, over MCP. This page covers its MCPB bundle (https://github.com/entire-vc/evc-mesh-mcp/releases/download/v0.1.8/evc-mesh-mcp-0.1.8.mcpb).

Is the io.github.entire-vc/evc-mesh-mcp server safe to use?

io.github.entire-vc/evc-mesh-mcp scores 52 out of 100 on VerifyMCP. 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 io.github.entire-vc/evc-mesh-mcp server expose?

io.github.entire-vc/evc-mesh-mcp exposes 36 tools: add_comment, add_note, add_vcs_link, answer_decision, archive_memory, and 31 more. Their descriptions and schemas cost roughly 11,797 tokens of context every time the server is loaded.

What licence is the io.github.entire-vc/evc-mesh-mcp server under?

io.github.entire-vc/evc-mesh-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.entire-vc/evc-mesh-mcp server?

VerifyMCP ran 12 checks on io.github.entire-vc/evc-mesh-mcp, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about io.github.entire-vc/evc-mesh-mcp: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.