Allows AI agents to manage and monitor overseer.nvim tasks in a Neovim instance, including listing, running, tailing, restarting, stopping, and disposing tasks.
An MCP server that gives a coding agent the same control over overseer.nvim tasks that you have: list, tail, run, restart, stop, and dispose.
Your agent's shell tool and your overseer task list are separate execution worlds. A dev server the agent starts in its own shell is invisible in the task list, can't be stopped from it, and orphans its process tree when the session ends. Tasks you start get proper teardown. This closes that gap: the agent's long-running commands become real overseer tasks.
Related MCP server: @aetherall/mcp-nvim-tmux
Neovim with overseer.nvim
(tested against v2.1.0)
Node >= 22
An MCP client running inside a Neovim terminal buffer
The server speaks stdio and is started by your MCP client. The command is always the same:
npx -y overseer-nvim-mcpThe client must run inside a Neovim terminal buffer; that is where the
$NVIM socket it inherits comes from. Tools appear at the next session start,
since MCP servers connect at startup. If the tools never appear, the usual
cause is that $NVIM did not reach the server's environment: the server
registers nothing without it, and some clients strip the environment they
pass to servers.
claude mcp add overseer -- npx -y overseer-nvim-mcpcodex mcp add overseer -- npx -y overseer-nvim-mcpThen add one line to the generated block in ~/.codex/config.toml:
[mcp_servers.overseer]
command = "npx"
args = ["-y", "overseer-nvim-mcp"]
env_vars = ["NVIM"]The env_vars line is required. Codex passes stdio servers a fixed whitelist
of variables (HOME, PATH, TERM and the like), $NVIM is not on it, and
without it the server registers no tools.
Codex also won't reach for the server on its own; see Getting your agent to actually use it.
In ~/.gemini/config/mcp_config.json:
{
"mcpServers": {
"overseer": {
"command": "npx",
"args": ["-y", "overseer-nvim-mcp"]
}
}
}That user-global file is the one to use: the CLI's non-interactive print mode
(agy -p) loads MCP servers from it and from nowhere else; a workspace-level
.agents/mcp_config.json is silently ignored there.
Antigravity also won't reach for the server on its own; see Getting your agent to actually use it.
gemini mcp add overseer npx -y overseer-nvim-mcpOr in settings.json:
{
"mcpServers": {
"overseer": {
"command": "npx",
"args": ["-y", "overseer-nvim-mcp"]
}
}
}In opencode.json:
{
"mcp": {
"overseer": {
"type": "local",
"command": ["npx", "-y", "overseer-nvim-mcp"]
}
}
}In mcphub's servers config:
{
"mcpServers": {
"overseer": {
"command": "npx",
"args": ["-y", "overseer-nvim-mcp"],
"env": { "NVIM": "${NVIM}" }
}
}
}The env block is required: mcp-hub does not pass its own environment to the
servers it spawns, so without it the server sees no $NVIM and registers no
tools. The server operates on the Neovim instance that started the hub. A hub
started outside Neovim has no $NVIM to forward, and mcp-hub reports this
server as disconnected with Variable 'NVIM' not found.
LazyVim ships an overseer.nvim extra.
Enable it with :LazyExtras (select editor.overseer), restart Neovim, then
add the server to your MCP client as above. Nothing else is needed; the server
talks to whatever overseer configuration you already have.
Tool | Purpose |
| Tasks with id, name, status, |
| Templates in a directory (npm, go-task, make, just, VS Code) with |
| A task's output, with status; can block until a pattern appears |
| Start a long-running command: a raw |
| Restart a task by id or name substring |
| Stop a running task |
| Stop and remove a task from the list |
The last three take force, and refuse a running task you started without it.
Tasks are addressed by numeric id or a case-insensitive name substring, so an
agent can say "dev" instead of tracking ids.
The transport is $NVIM, the RPC socket Neovim exports to every process it
spawns in a terminal buffer. Your MCP client inherits it, and this server, as a
child of that client, inherits it in turn.
Everything else follows from that:
With $NVIM set, the server registers seven tools, each one
nvim_exec_lua against overseer over msgpack-RPC.
With $NVIM unset, it registers nothing and gets out of the way. Running
outside Neovim is a no-op rather than an error.
There is no socket discovery: no cwd hashing, no lsof, no
pgrep. Those approaches are structurally broken (a cwd-hash scheme cannot tell
a crashed instance's stale socket from a live one and will unlink working
sockets; pgrep on macOS excludes the caller's own ancestors, which is exactly
the Neovim instance that matters). $NVIM sidesteps both by construction.
All user input (task names, commands, working directories) is passed as msgpack
arguments and arrives in Lua as .... Nothing is ever interpolated into Lua
source, so a task name cannot become code execution.
The task list has two writers now, and only one of them can see it. Two things keep that from biting:
A substring matching more than one task is an error that lists the
candidates and asks for a numeric id. "dev" matches a dozen names in a
monorepo, and silently taking the first is how the wrong thing gets stopped.
Tasks are tagged with who started them. overseer_list_tasks reports origin
as agent or user, and overseer_stop, overseer_restart and
overseer_dispose refuse a running task you started yourself unless
force is passed. Finished tasks are unguarded, since removing a dead row
costs nothing.
The asymmetry is on purpose. A wrong refusal costs one extra call. A wrong stop kills your dev server, loses whatever state it held, and you would have no reason to connect it to the agent.
overseer_run is for commands that do not exit on their own: dev servers,
file watchers, --watch test runs. Short commands that terminate by themselves
should stay on the agent's normal shell tool, where output is available in-band.
Round-tripping a two-second build through start-then-poll is worse.
overseer_list_templates returns whatever overseer's providers discover, verbatim.
Most repos declare nothing runnable and return an empty list. That is a
legitimate answer, not an error. This is why overseer_run takes a raw cmd as
its primary path: a template-only design would be unusable in the common case.
No provider-specific knowledge lives in this server. It does not filter or rewrite results, including help-only entries some task runners expose, because doing so would mean encoding one provider's conventions into a server that must behave identically in a repo that has never heard of it.
What each entry carries:
{
"name": "just fixture-just-generate",
"provider": "just",
"desc": "Generate output for a language",
"params": [{ "name": "lang", "type": "string", "required": true }],
"running_task_id": 128
}desc is an explicit null when a provider supplies no descriptions.
npm and make never do; go-task and just usually do. An explicit null says
there is nothing to read, rather than leaving you guessing whether a field got
dropped somewhere.
Entries with a description sort first. That encodes nothing about any provider, only about information content. A repo with a Taskfile and a package.json would otherwise bury its documented half beneath dozens of bare npm script names.
params are the arguments a template takes; required marks the ones
overseer_run will refuse the call without. Pass them as params. A missing
one is an error naming what it wanted rather than a prompt opened in your
editor.
running_task_id appears when a task of that name is already running.
It is a name match, so it can miss (a template invoked with params produces a
task named after the resolved command), but when it is there, it is the signal
not to start a second dev server on top of yours.
filter matches a substring against name and desc. Worth using: a
three-runner monorepo can return well over eighty entries.
On some clients this is automatic. The server returns MCP instructions in its
initialize result, and clients that surface those put them in the agent's system
prompt, where it is actually looking rather than buried among fifty tool
descriptions. It states the lifetime boundary (long-running here, short commands
on the shell) and tells the agent to check templates before reconstructing a
command, use wait_for instead of polling, and clean up only its own tasks.
The server withholds those instructions when $NVIM is unset, for the same
reason it registers no tools: a session that gets none should not be told how to
use them.
Whether the instructions reach the model is the whole game, and clients differ:
Claude Code injects them. Copilot CLI injects them for servers whose
instructions you allow (--allow-all-mcp-server-instructions in scripted
runs).
Codex CLI shows the model the tool definitions but not the instructions,
and leaving servers untouched until prompted is a known
open issue. Asked to "start
the dev server", it runs npm run dev in its own shell with the server
connected and working.
Antigravity CLI injects nothing at all: it writes the instructions and
every tool schema to files under ~/.gemini/antigravity-cli/mcp/overseer/
that the model only reads once something points it there. Same prompt, same
result: its own shell.
On those two, either name overseer in the prompt ("start the dev server in
overseer" works on both) or say it once in the place the client actually
reads: its context file. One line in AGENTS.md (Codex) or GEMINI.md (Antigravity)
flips the same prompt to full overseer routing: templates checked first, task
run by name, output tailed after.
The markdown below is that one-time instruction, and it belongs in your
project context file on every client (CLAUDE.md, AGENTS.md, GEMINI.md, whatever yours reads).
Clients re-read project instructions constantly, so they outweigh anything the
server can send:
## Long-running commands
Start dev servers, file watchers and `--watch` test runs with `overseer_run`,
not the shell. They then appear in my task list, I can stop them myself, and
their process trees get torn down properly instead of being orphaned.
Short commands that exit on their own stay on the shell: their output is
in-band there, which is what you want.
Check `overseer_list_templates` first. If the repo declares one that matches, run
it by name rather than reconstructing the command.If that still isn't enough, a PreToolUse hook makes it deterministic. This one
blocks the shell for a few unambiguous cases and tells the agent what to do
instead. Start narrow and add patterns you actually hit, since a hook that fires
on the wrong thing is worse than none:
#!/usr/bin/env bash
# ~/.claude/hooks/prefer-overseer.sh: exit 2 blocks the call and shows stderr
# to the agent. Receives the tool call as JSON on stdin.
cmd=$(jq -r '.tool_input.command // ""')
case "$cmd" in
*"vitest run"*) ;; # one-shot, stays on the shell
*" --watch"*|*"vitest"*|*"npm run dev"*|*"pnpm dev"*|*"yarn dev"*)
echo "This looks long-running. Use overseer_run so it lands in the task list and can be stopped." >&2
exit 2
;;
esac
exit 0{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [{ "type": "command", "command": "~/.claude/hooks/prefer-overseer.sh" }]
}
]
}
}An agent driving a task by hand ends up guessing: start it, tail, get nothing, tail again, get nothing. It has no way to sleep, so every guess is a round-trip you watch scroll past.
overseer_tail takes a wait_for regex instead. It returns the moment a
matching line appears, or when the task exits, or at timeout_ms, and says
which of the three happened, so a timeout can't be misread as success:
overseer_tail { task: 48, wait_for: "ready - listening" }
status=RUNNING total=5 from=1 waited=matched
compiling... 0
compiling... 1
compiling... 2
ready - listening on http://localhost:3000
GET /route-4 200total is a cursor. Pass it back as since and you get only what is new,
rather than re-reading the same screenful every poll:
overseer_tail { task: 48, since: 5 }
status=RUNNING total=9 from=6
GET /route-5 200
GET /route-6 200
GET /route-7 200
GET /route-8 200from is the index the block actually starts at. If it is greater than
since + 1, output scrolled past between calls and you are looking at a gap
rather than a continuation.
overseer_run waits briefly too, up to settle_ms (default 1500, 0 to
disable), returning as soon as the task produces output or exits. A command that
dies on startup reports its failure there instead of returning the same bare id
a healthy dev server would.
The waiting happens in Node. This server runs inside
your editor, and vim.wait does not process input, so a fifteen-second wait in
Lua would freeze your session for fifteen seconds. Polling over the local socket
keeps Neovim responsive, and you never see the round-trips.
Tools are what the agent calls. The server also publishes two things you drive.
Prompts appear as slash commands (/mcp__overseer__... in Claude Code). The
server generates them per invocation, so they inspect your live editor state
rather than reciting a generic answer:
directory_local_task defines a task for a project that has no npm
script, Makefile or Taskfile, using overseer's own register_template in a
.nvim.lua. It checks whether exrc is actually on and whether a .nvim.lua
already exists, and includes the two things that make a correct setup look
broken: it will not appear until Neovim restarts, and Neovim will ask you to
:trust the file.
diagnose explains why overseer is not showing the tasks you expect.
Overseer records, per provider, why it contributed nothing, and that reason is
otherwise invisible:
- `npm`: 11/11 available
- `make`: 0/0 available - No Makefile found
- `mise`: 0/0 available - Command "mise" not foundWhich distinguishes "nothing to read here" from "that runner isn't installed", a distinction an empty list cannot make.
Resources are attachable rather than called:
overseer://tasks: the whole task list as JSON
overseer://task/{id}/output: one task's output, with a status line
The server enumerates the per-task URIs with live ids and supports completion, so a client can offer the tasks that exist instead of making you look one up.
Output from a task started over RPC lives in the strategy's pending buffer, not
a terminal buffer, until you open the overseer panel. overseer_tail reads
both, strips ANSI colour codes and carriage returns, and trims the PTY's blank
padding so you get clean log lines rather than the bottom of an empty grid.
exit_code is absent while a task is running and present once it exits, which
is how an agent distinguishes a clean finish from a crash.
See CONTRIBUTING.md. Releases are automated with release-please, so commits must follow Conventional Commits.
MIT © Miguel Angelo Sepulveda
Stop (if running) and remove a task from the list by id or name substring. Disposing a finished task is unguarded; a running one the user started is refused unless force is set. A name matching more than one task is an error.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | ||
| force | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (idempotent, destructive), the description discloses important behaviors: it refuses to dispose a running user-started task unless force is set, treats name ambiguity as an error, and notes that disposing a finished task is unguarded. This provides critical safety and edge-case context that could affect invocation.
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?
Three sentences, front-loaded with the main action, and no redundant phrasing. Every sentence contributes new information (operation, guard behavior, error case), making it efficient and easy to parse.
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?
The description is self-contained for a destructive, idempotent operation. It covers the core action, parameter semantics, edge cases, and guard conditions. With no output schema, it still offers enough insight for an agent to decide and invoke correctly, especially given the sibling context and annotations.
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?
With 0% schema description coverage, the description effectively explains both parameters: 'task' can be an id (integer) or name substring (string), and 'force' overrides the refusal for running tasks. It also clarifies that a name matching multiple tasks causes an error, which adds meaning beyond the raw schema.
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 clearly states the tool stops and removes a task from the list, using the verb 'dispose' and specifying the resource (task) and operation (stop/remove). It distinguishes itself from sibling tools like overseer_stop (which only stops) and overseer_restart (which restarts) by focusing on removal.
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 context for when to use the tool (to stop and remove a task) and implies a distinction from overseer_stop by including 'remove,' but it does not explicitly name alternatives or state when not to use it. The guard conditions (refusal for running user-started tasks without force) add useful situational guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List running and completed overseer.nvim tasks (id, name, status), newest first. origin is 'agent' for tasks this server started and 'user' for the ones they started themselves; only clean up your own.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context: the ordering is newest first, the origin field distinguishes agent-started vs user-started tasks, and it explicitly warns to clean up only your own tasks. No contradiction exists between the description and annotations.
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 two concise sentences that front-load the core purpose ('List running and completed overseer.nvim tasks') and immediately provide ordering and fields. The second sentence adds essential origin semantics without any filler.
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?
For a zero-parameter list operation with a read-only annotation, the description is fully sufficient. It names the returned fields, ordering, origin semantics, and cleanup guidance, covering what an agent needs to use the tool correctly despite the lack of an output schema.
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 and the schema description coverage is 100%, so the description is not required to explain parameters. It correctly focuses on behavior rather than parameter details, meeting the baseline for no-parameter tools.
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 clearly states the tool lists running and completed overseer.nvim tasks with id, name, and status, newest first. This specific verb+resource combination distinguishes it from sibling tools like overseer_run, overseer_stop, and overseer_list_templates.
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 implies when to use this tool: to inspect tasks and determine which ones the agent owns before cleanup, as indicated by 'only clean up your own.' It gives useful context about origin values but does not explicitly name alternative tools or state when not to use it, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List task templates overseer discovers in a directory (npm scripts, go-task, make, just, VS Code tasks, etc). An empty list is normal (many repos declare nothing runnable); use overseer_run with a raw cmd instead. Each entry has provider (which task runner it came from) and desc, which is null when that provider supplies no descriptions (npm and make never do, go-task and just usually do), so a null desc means there is nothing to read, not that something was withheld. Entries that have a description are listed first. params lists arguments a template takes, with required marking those that overseer_run will reject the call without. running_task_id is present when a task of that name is already running, which is your signal not to start a second one. Pass filter to match a substring against name and desc; worth doing in a large monorepo, where this can return well over eighty entries.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Directory to search; defaults to nvim's current working directory | |
| filter | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description explains non-obvious behaviors: null 'desc' means the provider doesn't give descriptions (not withheld), entries with descriptions are listed first, and 'running_task_id' signals an already-running task to avoid duplicates. These are valuable behavioral details not captured in annotations.
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 intentionally dense but every sentence adds value: purpose, empty-list caveat, field semantics, ordering, and filter guidance. It avoids repeating schema content and is well-structured, though slightly long; it earns its length.
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?
With no output schema, the description carries the burden of explaining return values. It covers the key fields (provider, desc, params, running_task_id) and their meanings, plus ordering and edge cases. It doesn't enumerate every possible field, but it gives the agent enough to understand the response and decide next steps.
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 schema documents cwd but leaves 'filter' undescribed. The description compensates by explaining that 'filter' matches a substring against name and desc and is useful for narrowing large result sets, adding meaning beyond the schema. It doesn't add detail for cwd, but that's already covered well.
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 opens with 'List task templates overseer discovers in a directory' which clearly states the verb, resource, and scope. It distinguishes itself from siblings by focusing on templates (not tasks) and explicitly mentions overseer_run as an alternative for raw commands.
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?
It provides explicit when-to-use guidance: 'An empty list is normal... use overseer_run with a raw cmd instead.' It also advises using the 'filter' parameter in large monorepos to handle results exceeding eighty entries, giving clear context for when to apply the filter.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Restart a task by id or name substring (stops it first if running). A name matching more than one task is an error listing the candidates; pass a numeric id instead. Running tasks the user started are refused unless force is set.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | ||
| force | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the destructiveHint annotation, the description discloses important behaviors: automatic stop-before-restart, ambiguous-name error listing candidates, and refusal of user-started running tasks unless force is set. This significantly enriches the agent's understanding of side effects and restrictions.
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?
Three concise sentences, each carrying essential information without redundancy. Front-loaded with the primary action and followed by necessary caveats and error behavior.
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?
The description is complete for a restart operation: it covers input selection, error conditions, and safety restrictions. No output schema is present, but return values are not critical for this destructive action, and the description provides enough context for correct invocation.
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?
Despite zero schema description coverage, the description explains both parameters: task can be a numeric id or name substring, and force overrides the refusal of running user-started tasks. This fully compensates for the schema's lack of descriptive text.
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 clearly states the tool restarts a task by id or name substring, using a specific verb and resource. It distinguishes itself from sibling tools like overseer_stop by explicitly noting it stops the task first if running.
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 gives practical usage guidance: use a numeric id when a name matches multiple tasks, and set force to override refusal of user-started running tasks. It does not explicitly contrast with alternatives but provides clear contextual usage rules.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Start a long-running command as an overseer task, so it appears in the user's task list, can be stopped from it, and inherits proper process-group teardown. Use for commands that DO NOT exit on their own: dev servers, file watchers, --watch test runs, log tails. For short commands that terminate by themselves, use Bash instead: you need their output in-band, and round-tripping a fast build through start-then-poll is worse. Pass exactly one of template or cmd. Prefer template (a name from overseer_list_templates) when one matches what you want; it runs the repo's own definition under the name the user already sees in their task list. Most repos declare no templates, in which case pass cmd as an argv array, which works anywhere. Note a cmd is a one-off, though: gone when the session ends, and the user cannot run it again without you. If they want it to persist, it belongs in a directory-local template instead of being re-passed as cmd every time; the server instructions describe how. cmd does not go through a shell, so for pipes, globs, && or env prefixes pass an explicit wrapper: ["sh", "-c", "..."]. Returns once the task has produced output or exited, up to settle_ms (default 1500, 0 to return immediately), so a command that dies on startup reports its failure here rather than looking identical to a healthy one until some later tail. Templates that declare params need them supplied here; pass params as an object of name to value. A missing required param comes back as an error naming what it wanted rather than a prompt opening in the editor.
| Name | Required | Description | Default |
|---|---|---|---|
| cmd | No | ||
| cwd | No | Working directory for the task; for `template`, also the directory the template is resolved in. Defaults to nvim's cwd | |
| name | No | Task-list name for a `cmd` task; defaults to the command. A `template` runs under its own name | |
| params | No | ||
| template | No | ||
| settle_ms | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses many behavioral traits beyond the minimal annotations: the task appears in the task list, can be stopped, inherits teardown, `cmd` bypasses the shell, the call blocks until output/exit up to `settle_ms`, startup failures are reported, and missing required template params return an error. This is rich context not present in the annotation.
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?
Although the description is long, it is densely packed with necessary information and each sentence addresses a distinct concern: use case, alternative, parameter selection, persistence, shell behavior, return behavior, and error handling. It is front-loaded with purpose and usage, and there is no filler.
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 complexity (6 parameters, nested objects, template vs cmd alternatives, no output schema), the description is complete enough for an agent to select and invoke it correctly. It covers prerequisites, side effects, return semantics, failure handling, and persistence, leaving no significant operational gap.
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 coverage is only 33%, but the description compensates by explaining the key parameters: `template` vs `cmd` exclusivity, `cmd` as an argv array not through a shell, `params` as a name-to-value object for templates, and `settle_ms` default and zero behavior. It also clarifies `cwd` resolution for templates beyond the schema.
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 opens with a specific verb and resource ('Start a long-running command as an overseer task') and clearly differentiates the tool from siblings by stating what it does that others don't: appear in the user's task list, be stoppable, and get proper process-group teardown. It also contrasts with Bash for short commands, which removes ambiguity.
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?
Explicit guidance is given on when to use this tool vs alternatives: use for commands that do not exit on their own, use Bash for short terminating commands. It further instructs when to prefer `template` over `cmd`, how to handle shell features with `sh -c`, and warns about `cmd` being a one-off, with an alternative for persistence.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Stop a running task by id or name substring. Overseer stops the underlying nvim job, so the task's process tree is torn down rather than left orphaned. A name matching more than one task is an error listing the candidates. Running tasks the user started are refused unless force is set, since a substring like 'dev' can match theirs.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | ||
| force | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (idempotentHint, destructiveHint), the description explains that stopping a task tears down the underlying process tree, that ambiguous names result in an error listing candidates, and that user-owned tasks are refused without force. This adds significant behavioral context.
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?
Three dense sentences with no filler; each provides distinct information about the tool's operation.
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 simple 2-parameter tool with no output schema, the description covers the action, matching behavior, underlying process implications, error handling, and force flag, making it self-contained.
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 has no descriptions (0% coverage), but the description clarifies that 'task' accepts an id or name substring, and 'force' overrides refusal for user-started tasks. This fully compensates for the schema gap.
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 uses the specific verb 'Stop' and identifies the resource as 'a running task' with the method 'by id or name substring'. It clearly differentiates from sibling tools like overseer_run (start) and overseer_restart (restart).
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 conditions: multiple matches cause an error, and stopping tasks started by others requires force. However, it does not explicitly reference alternative tools for starting/restarting tasks, so it lacks explicit vs-alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return a task's live output, preceded by a status line. task is a numeric id or a case-insensitive name substring; omit it for the most recent task. The status line reports status, exit_code once the task has exited, and total (lines available so far), so you never need a separate overseer_list_tasks to find out whether what you are tailing is still alive. Pass the previous total back as since to get only what is new instead of re-reading the same lines; from tells you where the returned block actually starts, and a from greater than since + 1 means output scrolled past between calls. Set wait_for to a regular expression to block until a matching line appears; use it instead of polling repeatedly. It returns as soon as it matches, or when the task exits, or at timeout_ms (default 15000, max 120000), and reports which of the three happened as waited, so a timeout is never mistaken for success.
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | ||
| lines | No | Trailing lines to return; default 10. Pass more when diagnosing a failure, e.g. 100 for a stack trace with its footer | |
| since | No | ||
| wait_for | No | ||
| timeout_ms | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses rich behavioral details: the status line contents (status, exit_code, total), the behavior of `since`/`from` for incremental output and detecting scroll-past, the blocking behavior of `wait_for`, timeout defaults and max, and the `waited` field distinguishing match/exit/timeout. This fully discloses the tool's runtime behavior without contradicting annotations.
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 front-loaded with the core purpose and then systematically covers each parameter and behavioral nuance. Every sentence adds value, and the structure flows logically: purpose, task selection, status line, incremental reading, wait_for behavior, and timeout semantics. Despite its length, it is tightly written with no filler.
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?
With no output schema and low schema parameter coverage, the description carries the full burden for explaining inputs and outputs. It explains return values (status line, `from`, `waited`), parameter behavior, and edge cases (scroll-past detection). The tool is complex, and the description is complete enough for an agent to invoke it correctly.
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 coverage is only 20% (only `lines` has a description), but the tool description compensates thoroughly: it explains `task` (numeric id or case-insensitive name substring, omit for most recent), `since` (pass previous total to get new lines), `wait_for` (regex to block until match), and `timeout_ms` (default 15000, max 120000). This adds substantial meaning beyond the raw schema.
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 clearly states 'Return a task's live output, preceded by a status line.' This specifies the verb (return/tail), resource (task output), and distinguishes it from sibling tools like overseer_list_tasks or overseer_run. The differentiation is explicit: 'so you never need a separate overseer_list_tasks to find out whether what you are tailing is still alive.'
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 gives explicit when-to-use guidance: it tells you to use `wait_for` instead of repeated polling, and explicitly notes you don't need overseer_list_tasks for status. It also explains when to omit `task` (for the most recent task) and how to use `since` for incremental reads. This covers both alternatives and usage context clearly.
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. Dates show when Glama detected each change.
v0.2.1overseer_list_templates1 field changedInput schema / properties / cwd / descriptionAdded value: +"Directory to search; defaults to nvim's current working directory"overseer_run2 fields changedInput schema / properties / cwd / descriptionAdded value: +"Working directory for the task; for `template`, also the directory the template is resolved in. Defaults to nvim's cwd"Input schema / properties / name / descriptionAdded value: +"Task-list name for a `cmd` task; defaults to the command. A `template` runs under its own name"overseer_tail1 field changedInput schema / properties / lines / descriptionAdded value: +"Trailing lines to return; default 10. Pass more when diagnosing a failure, e.g. 100 for a stack trace with its footer"v0.2.0overseer_disposeoverseer_list_tasksoverseer_list_templatesoverseer_restartoverseer_runoverseer_stopoverseer_tailEach tool targets a distinct operation: listing tasks, listing templates, tailing output, running, restarting, stopping, and disposing. The lifecycle tools (restart/stop/dispose) have clear boundaries: restart stops then starts, stop just stops, dispose removes entirely. Descriptions eliminate confusion, such as noting that name substrings can match multiple tasks and require an id.
All tools share the 'overseer_' prefix, and the actions are clear verbs: list, tail, run, restart, stop, dispose. The pattern is mostly consistent: 'overseer_list_tasks' and 'overseer_list_templates' use verb_noun, while the others use verb alone (implied 'task'). This is a minor deviation but predictable and readable.
Seven tools is well within the ideal 3-15 range for a task manager. Each tool covers an essential operation with no redundancy or excess. The scope matches the domain of managing Neovim overseer tasks.
The toolset covers the full task lifecycle: create (run), read (list_tasks, list_templates, tail), update (restart), stop (stop), and delete (dispose). Tail also provides status and exit codes, so no separate status tool is needed. The description notes that short commands should use Bash instead, indicating deliberate design rather than an omission.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/impossiblecode/overseer-nvim-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
